Artificial intelligence All MCQ's -(Part-3)

AKTU Artificial Intelligence For Engineering(KMC 101/KMC 201 )

Assignment -1

Q:1. A.M. Turing developed a technique for determining whether a computer could or could

not demonstrate the artificial Intelligence, Presently, this technique is called __________

1.Turing Test

2.Algorithm

3.Boolean Algebra

4.Logarithm

Solution- 1. Turing Test

Reason 1- The test is known as after Turing , the founding father of the Turing Test and an

English scientist , cryptanalyst, mathematician and theoretical biologist.

Q:2. Knowledge based systems comprises of:

1.DENDRAL

2.MYCIN

3.PROSPECTOR

4.All the above

Solution- 1. DENDRAL

Reason 1- The DENDRAL programs were knowledge-driven, within the sense of today’s expert

systems, with the knowledge principle–that knowledge is power-first articulated within the context of

DENDRAL

Q:3. Weak AI is

1.A set of computer programs that produce output that would be considered to reflect intelligence if it

were generated by humans.

2.Useful for testing hypothesis about minds, but would not actually be minds

3.The embodiment of human intellectual capabilities within a computer.

4.None of the above

Solution- 2.Useful for testing hypothesis about minds, but would not actually be minds

Reason 1- Weak AI lacks human consciousness, although it’s going to be ready to simulate

it sometimes .

Q:4. Strong AI is

1.An AI system with generalized human cognitive abilities.

2.Also called as narrow AI.

3.All actions are preprogrammed by human

4.None of the above

Solution- 1.An AI system with generalized human cognitive abilities.

Reason 1- Strong AI include the ability to reason, solve puzzles, make judgments, plan, learn, and

communicate. It should also have consciousness, objective thoughts, self-awareness, sentience, and

sapience. Strong AI is also called True Intelligence or Artificial General Intelligence (AGI)

Q:5. Which of the following could be the approaches to Artificial Intelligence?

1.Strong AI

2.Swarm Intelligence

3.Computational Intelligence

4.All the above

Solution- 4. All of the Above

Reason 1- Artificial Intelligence comprises of the following abilities such as Strong A.I, Swarm

Intelligence and computational Intelligence.

Q:6. AI vs. Human Brain

1.Humans use content memory and thinking whereas, robots are using built-in instructions, designed

by scientists.

2.Artificial intelligence cannot beat human intelligence at all

3.The field of Artificial intelligence limits on designing machines that can mimic human behavior.

4.None of the above

Solution- 3.The field of Artificial intelligence limits on designing machines that can mimic

human behavior.

Reason 1- Because these machines are harder to implement and requires tons of memory usage and

processing power.

Q:7. Which of the following is not a stage of AI?

1.Cognitive analytics

2.Predictive analytics

3.Diagnostic analytics

4.None of the above

Solution- 1. Cognitive Analytics

Reason 1- Cognitive Computing tries to replicate how humans would solve problems while AI seeks

to create new ways to solve problems that can potentially be better than humans.

Q:8. Steps to process the command are:

1.Trigger word detection

2.Speech recognition

3.Intent recognition

4.All the above

Solution 4- All of the above

Reason 1- All of the command that are written within the above option are the steps to process the

commands.

Q:9. Which of the following is not an application of AI?

1.Pattern recognition

2.Crop prediction

3.Digital assistant

4.Fund transfer

Solution- 4.Fund transfer

Reason 1- As we know pattern recognition, crop prediction, digital assistant all come under the

application of A.I but fund transfer is the process that is done using pre programmed instructions.

Q:10. A method of programming a computer to exhibit human intelligence is called modeling

or…………………

1.simulation

2.cognitization

3.duplication

4.psychic amelioration

Solution- 1. Simulation

Reason 1- because the production of a computer model of something, especially for the purpose of

study is known as Simulation.

AKTU Artificial Intelligence For Engineering(KMC 101/KMC 201 )

Assignment -2

Q:1. What is an advantage of Artificial Intelligence?

1.Potential for misuse

2.Highly dependent on machines

3.Requires Supervision

4.Rational Decision Maker

Solution- 4- Rational Decision Maker

Reason 1- This is because Rational choice theory in A.I. states that it rely on rational calculations to

make rational choices that result in outcomes aligned with their own best interests.

Q:2. Who is known as the “Father of AI”?

1.Fisher Ada

2.Alan Turing

3.John McCarthy

4.Allen Newell

Solution- 3.John McCarthy

Reason 1- John McCarthy, widely recognized as the father of Artificial Intelligence due to his

astounding contribution in the field of Computer Science and AI.

Q:3. Which of the following is not a branch of Artificial Intelligence?

1.Expert systems

2.Robotics

3.Natural language Processing

4.None of the above

Solution- 4.None of the above

Reason 1- This is because Expert System, Robotics and Natural Language processing all have their

roles in Artificial Intelligence. There are 6 branches of A.I and these 3 above come under these

branches.

Reason 2- This is because Expert System, Robotics and NLP all have their roles in AI . There are 6

branches of A.I and these 3 above come under these branches.

Q:4. Which of the following is not an application of Unsupervised Learning?

1.Document clustering

2.Speech recognition

3.Image compression

4.Association analysis

Solution- 4. Speech Recognition

Reason 1- This is the kind of application where you teach the algorithm about your voice and it will

be able to recognize you. The most well-known real-world applications are virtual assistants such as

Google Assistant and Siri, which will wake up to the keyword with your voice only. That is the reason

it comes under supervised learning.

Q:5. The multi-armed bandit problem is a generalized use case for1.Reinforcement learning

2.Supervised learning

3.Unsupervised learning

4.All the above

Solution- 1.Reinforcement learning

Reason 1- Multi–Arm Bandit is a classic reinforcement learning problem, in which a player is facing

with k slot machines or bandits, each with a different reward distribution, and the player is trying to

maximise his cumulative reward based on trials.

Q:6. Why IOT now?

1.Electronic companies are building Wi-Fi and cellular wireless connectivity into a wide range of

devices.

2.Mobile data coverage has improved significantly

3.The size and cost of wireless radios has dropped

4.All the above

Solution- 4. All the above

Reason 1- All of the above options that have provided in this question are correct and helping IOT to

evolve in the future.

Q:7. Scalability of IoT means:

1.Expandable/reducible in terms of scale or size.

2.Measurable

3.Increasing/decreasing monetary costs.

4.All of these.

Solution- 4. All of these.

Reason 1- This is because the IOT is expandable/reducible in size or to scale. It is also measurable

and its cost can be increased or decreased.

Q:8. Which of the following statement is incorrect for AI?

1.Humans can not evolve as soon as AI evolves to control and handle it

2.The community working towards safe and beneficial superintelligence has grown worldwide.

3.It is typically managed by a peer-to-peer network working simultaneously together to solve complex

mathematical problems in order to validate new blocks

4.AI is the new electricity

Solution- 1.Humans can not evolve as soon as AI evolves to control and handle it

Reason 1- We cannot say humans cannot evolve to control and handle it because humans are working

on it regularly to make an A.I that will reduce their workload and time to complete a task, which they

will adapt later.

Q:9. Overfitting

1.The model remembers a huge number of examples instead of learning to notice features and may

fail to predict future observations reliably.

2.Occurs when a statistical model cannot adequately capture the underlying structure of the data.

3.Occurs if the model or algorithm shows low variance but high bias

4.None of the above

Solution- 1.The model remembers a huge number of examples instead of learning to notice

features and may fail to predict future observations reliably.

Reason 1- Overfitting is “the production of an analysis that corresponds too closely or exactly to a

particular set of data, and may therefore fail to fit additional data or predict future observations

reliably”

Q:10. AI in security will:

1.Not detect threats based on application behavior and a whole network’s activity.

2.Not be able to identify and stop cyber threats with less human intervention than is typically expected

or needed with traditional security approaches.

3.Not detect when new threats are imminent

4.Not replace a security analyst’s insights or understanding of the field.

Solution- 4. Not replace a security analyst’s insights or understanding of the field.

Reason 1- This is because we do not have A.I’s that can understand and gathered field intelligence

without human intervention.

AKTU Artificial Intelligence For Engineering(KMC 101/KMC 201 )

Assignment -3

Q:1. The first usage of Data came in:

1.1640

2.1954

3.1946

4.1940

Solution- 3. 1946

Reason- The first English use of the word “data” is from the 1640s. The word “data” was first used

to mean “transmissible and storable computer information” in 1946.

Q:2. DIKW:

1.Stands for Data, Information, Knowledge, Wisdom

2.In 1994 Nathan Shedroff presented the DIKW hierarchy in an information design context

3.In this context data is considered as symbols representing signals

4.All the above statements are correct

Solution- 1.Stands for Data, Information, Knowledge, Wisdom

Reason 1- Knowledge Pyramid, Wisdom Hierarchy and Information Hierarchy are some of the names

referring to the popular representation of the relationships between data, information, knowledge and

wisdom in the Data, Information, Knowledge, Wisdom (DIKW) Pyramid.

Q:3. Classification data type which is not on the basis of measurement:

1.Ratio data

2.Ordinal data

3.Boolean data (True/False)

4.Interval data

Solution- 3. Boolean data (True/False)

Reason- There are four levels of data measurements in classification data type: Nominal, Ordinal,

Interval, and Ratio.

Q:4. Not a case of Qualitative vs Quantitative data:

1.Category vs Number

2.Observed vs Measured

3.Smell vs Height

4.Volume vs Color

Solution- 4.Volume vs Color

Reason 1- Quantitative data can be counted, measured, and expressed using numbers. Qualitative

data is descriptive and conceptual. Qualitative data can be categorized based on traits and

characteristics.

Q:5. User driven approach is

1.Data Mining

2.Deep Learning

3.OLTP

4.Machine Learning

Solution- 3.OLTP

Reason 1- Current data warehouse development methods. can fall within three basic groups: data –

driven, goal-driven and user–driven. Implementation strategies.

Q:6. Physical storage of data:

1.CD-ROM

2.Distributed database

3.Cloud storage

4.None of the above

Solution- 1.CD-ROM

Reason 1- Physical (non-electronic) data may be stored in a variety of forms including photographs,

film, optical media (e.g. CDs & DVDs), magnetic media (e.g. audio and video tapes or computer

storage devices), artworks, paper documents or computer printouts.

Q:7. Which of the following statement is true for Data Warehouse?

1.It is semi-structured and raw

2.It is less agile with fixed configuration

3.It is designed for low-cost storage

4.All the above

Solution- 2.It is less agile with fixed configuration

Reason 1- A data warehouse is a highly structured data bank, with a fixed configuration and little

agility. Changing the structure isn’t too difficult, at least technically, but doing so is time consuming

when you account for all the business processes that are already tied to the warehouse.

Q:8. Importance of data:

1.It helps to analyze and visualize the performance

2.It helps to recommend correct options to the customers

3.It helps to solve complex problems

4.All the above

Solution- 4.All the above

Reason- All of the above steps are true in case of data. It helps us to in all the cases.

Q:9. Choose an incorrect statement:

1.ETL stands for Extraction, Transformation, Loading into repository.

2.Data cleaning is very important in data preparation.

3.Removal of outliers and smoothing of data is required to prepare data for further processing.

4.Data needs to be normalize.

Solution- 4.Data needs to be normalize.

Reason 1- Similarly, the goal of normalization is to change the values of numeric columns in the

dataset to a common scale, without distorting differences in the ranges of values. For machine

learning, every dataset does not require normalization. It is required only when features have

different ranges.

Q:10. Data visualization tools are:

1.Pie chart

2.Histogram

3.Scatter Plot

4.All the above

Solution- 4.All the above

Reason 1- Because data visualization tools are used to represent data in pictorial form. and all the

option above are used to represent data in visual form.

Assignment -4

Q:1. In Supervised Learning:

1.Input data is called training data and has a known label.

2.It can solve the classification and regression problems.

3.The training process continues until model achieves desired accuracy

4.All the above statements are true.

Solution- 4.All the above statements are true.

Reason 1- All the three 1,2, and 3 statements are true. As in supervised learning input data is called

training data and has a known label. This is also used to solve the classification and regression

problems. This training process continues until model achieves desired accuracy.

Q:2. In Unsupervised Learning, the incorrect statements are:

1.It organize data by similarity.

2.Input data know about results

3.It can solve problem of dimension reduction.

4.None of the above

Solution- 4.None of the above

Reason 1- This is because it organizes data by similarity and the input data know about the result. It

is also used to solve dimensionality problem.

Q:3. Data Visualization is:

1.Used to communicate information clearly and efficiently to users by the usage of information

graphics such as tables and charts.

2.Helps users in analyzing a large amount of data in a simpler way.

3.Makes complex data more accessible, understandable, and usable.

4.All of the above

Solution- 4. All of the above

Reason 1- All the reason that has been provided above are true. because Data visualization is a

process of representing data into pictorial or graphical form.

Q:4. Data Visualization tool that can be used for displaying hierarchical data:

1.Histogram

2.Treemap

3.Scatter plot

4.Pie chart

Solution- 2.Treemap

Reason 1- Treemaps are visualizations for hierarchical data. They are made of a series of nested

rectangles of sizes proportional to the corresponding data value.

Q:5. Which of the following is a Regression problem?

1.Weather forecasting

2.Spam/Not-Spam emails categorization

3.Sentiment analysis

4.Fraud detection

Solution- 4. Fraud Detection

Reason 1- In order to effectively test, detect, validate, correct error and monitor control systems

against fraudulent activities, businesses entities and organizations rely on specialized data analytics

techniques such as data mining, data matching, sounds like function, Regression analysis, Clustering

analysis and Gap.

Q:6. Which of the following is a Classification problem?

1.Estimating the price of house

2.Credit/loan approval

3.Recommender system

4.Predicts the number of items which a consumer will probably purchase

Solution- 2. Credit/loan approval

Reason 1- Classification algorithms work by predicting the best group to which a data point belongs

to by learning from labeled observations. It uses a set of input features for the learning process.

Classification algorithms are good for grouping data that are never seen before into their various

groupings and are therefore extensively used in machine learning tasks.

Q:7. Decision tree:

1.Belongs to a family of unsupervised learning algorithms

2.Consider all attributes to split at each node, starting from the root node

3.Create a model that can be used to predict the class or value of the target variable by learning simple

decision rules inferred from training data

4.All the above

Solution- 3.Create a model that can be used to predict the class or value of the target variable by

learning simple decision rules inferred from training data

Reason 1- because it is used to create a model that can be used to predict the class or value of the

target variable by learning simple decision rules inferred from training data

Q:8. Bayesian Classifier:

1.Connects the degree of belief in a hypothesis before and after accounting for evidence

2.Uses conditional and marginal probability

3.Performance can be estimated using accuracy, precision, recall

4.All the above

Solution- 4.All the above

Reason 1- This is because Bayesian Classifier uses conditional and marginal probability. Also it

connects the degree of belief in a hypothesis before and after accounting for evidence. And its

performance can be estimated using accuracy, precision, recall. That is the reason all the above

options are true.

Q:9. When two clusters have a parent-child relationship then it is called as:

1.K-means clustering

2.Fuzzy c-means clustering

3.Hierarchical clustering

4.Density based clustering

Solution- 3.Hierarchical clustering

Reason 1- When two clusters have parent-child relationship or tree like structure then it is called as

Hierarchical Clustering.

Q:10. Recommender system is an example of:

1.Clustering

2.Supervised learning

3.Reinforcement learning

4.Regression

Solution- 2. Supervised learning

Reason 1- The previous recommendation algorithms are rather simple and are appropriate for small

systems. Until this moment, we considered a recommendation problem as a supervised machine

learning task.

AKTU Artificial Intelligence For Engineering(KMC 101/KMC 201 )

Assignment -5

Q:1. The possible features of a text corpus in NLP

1.Count of the word

2.Identifying stop words

3.Predicting parts of Speech

4.All the above

Solution- 4.All the above

Reason 1- All of the above options are true.

Q:2. Normalization techniques in NLP

a. Lemmatization

b. Bag of words

c. Stemming

d. Named entity recognition

1.a,b

2.a,c

3.d,b

4.b,c

Solution- 2. a,c

Reason 1- In NLP a highly overlooked preprocessing step is text normalization. and Lemmatization

on the surface is very similar to stemming, where the goal is to remove inflections and map a word to

its root form. So these two are the normalization techniques in NLP.

Q:3. NLP Use cases

a. Text summarization

b. Object detection

c. Sentiment analysis

d. Chatbots

1.b,c,d

2.a,b,d

3.a, c, d

4.a,b,c

Solution- 3. a, c, d

Reason 1- Text summarization, Sentiment analysis and chatbots all uses natural language processing.

Q:4. Speech recognition

1.It is a way of encoding and decoding signals

2.It is coupled with AI as deep learning models

3.Both acoustic modeling and language modeling are important parts of modern statistically-based

speech recognition algorithms.

4.All the above

Solution- 4. All the above

Reason 1- This is because in speech recognition, encoding and decoding signals is done and it is also

coupled with AI as a deep learning model. and both the acoustic modeling and language modeling are

important parts of modern statistically-based speech recognition algorithms.

Q:5. Choose an incorrect statement in context of speech recognition

1.In 1952, three Bell Labs researchers built a system called “Audrey”

2.Modern general-purpose speech recognition systems are based on Hidden Markov Models

3.It can identify objects, people, places, and actions in images

4.None of the above

Solution 3- It can identify objects, people, places, and actions in images

Reason 1- This is because speech recognition do not identify objects, people, places, and actions in

images. This identification is done by object recognition and face recognition.

Q:6. Natural Language Understanding (NLU)

a. It is the ability of machines to understand the human language

b. It is a branch of Natural Language Processing

c. Natural-language understanding is considered an AI-hard problem.

d. None of the above

1.a,b,c

2.a,c,d

3.b,a,d

4.b,c,d

Solution- 1.a,b,c

Reason 1- NLU is a branch of NLP and it is considered an AI hard problem. It is the ability of

machines to understand the human language

Q:7. Speech recognition steps include

1.Feature extraction

2.Spectrum analysis

3.Preprocessing of input signals

4.All the above

Solution- 4. All the above

Reason 1- Speech recognition process takes place in three main steps which are acoustic processing,

feature extraction and classification/recognition. It also include spectrum analysis and preprocessing

of input signals.

Q:8. The interpretation capabilities of a language-understanding system depend on

1.The semantic Theory

2.The syntactic theory

3.Both a and b

4.None of the above

Solution- 1. The semantic Theory

Reason 1- The interpretation capabilities of a language-understanding system depend on the semantic

theory it uses. Semantic parsers convert natural-language texts into formal meaning representations.

Q:9. Applications of NLU

a. Automated reasoning

b. Machine translation

c. Network congestion control

d. All the above

1.c,d

2.b,c

3.d,a

4.a,b

Solution- 4.a,b

Reason 1- Before a computer can process unstructured text into a machine-readable format, first

machines need to understand the peculiarities of the human language. It gives machines a form of

reasoning or logic, and allows them to infer new facts by deduction. Simply put, using previously

gathered and analyzed information, computer programs are able to generate conclusions.

Q:10. Methods used in speech recognition systems are

1.Hidden Markov Model (HMM)

2.Neural Networks

3.Both a and b

4.None of the above

Solution- 3. Both a and b

Reason 1- at CMU, Raj Reddy’s students James Baker and Janet M. Baker began using the Hidden

Markov Model (HMM) for speech recognition. speech recognition was still dominated by traditional

approaches such as Hidden Markov Models combined with feedforward artificial neural networks.

AKTU Artificial Intelligence For Engineering(KMC 101/KMC 201 )

Assignment -6

Q:1. Choose an incorrect statement in context to Natural Language Generation (NLG)

1.Transforms structured data into natural language

2.Markov chains can be used for generating natural language

3.It converts a text into structured data

4.None of the above

Solution- 1.Transforms structured data into natural language

Reason 1- Natural Language Generation (NLG), a subcategory of Natural Language Processing

(NLP), is a software process that automatically transforms structured data into human-readable text.

Q:2. In natural-language understanding, the system needs to disambiguate the input sentence to

produce the machine representation language, in NLG the system needs to make decisions about how

to put a concept into words

1.True

2.False

Solution- 1. True

Reason 1- In natural language understanding the system needs to disambiguate the input sentence to

produce the machine representation language, whereas in Natural Language Generation the system

needs to make decisions about how to put a concept into words.

Q:3. Applications of Natural Language Generation

a. Smartphone

b. Analysis of business intelligence

c. IOT devices

d. Chatbots

1.a, b, c, d

2.a,c,d

3.b,c

4.a,b,c

Solution- 1.a, b, c, d

Reason 1- All the above application given in the option are true and these are the applications of

NLG.

Q:4. Choose correct options

a. NLU takes up the understanding of the data based on grammar, the context in which it was said and

decide on intent and entities.

b. NLP converts a text into structured data.

c. NLG generates a text based on structured data.

d. None of the above

1.b,c,d

2.a,c

3.a,b,c

4.a,b,d

Solution- 3.a,b,c

Reason 1The way these three of them work hand in hand are given as- NLU takes up the understanding of the

data based on grammar, the context in which it was said and decide on intent and entities. NLP will

convert the text into structured data. NLG generates text generated based on structured data.

Q:5. Chatbots

a. Can be used for E-commerce

b. Can be used to solve people’s travel related problems

c. Need not to pass the industry standard Turing test at any level

d. Require a large amount of conversational data to train

1.b,c,d

2.a,c

3.a, b, c

4.a,b,d

Solution- 4.a,b,d

Reason 1- Chatbots can be used for E-commerce and to solve people’s travel related problems but it

require a large amount of conversational data to train.

Q:6. Machine translation

a. Is the process of using computer programs to translate a text/speech from one natural language to

another relevant to context

b. It has the ability to translate in many languages

c. It is required for web content and web page translation

d. None of the above

1.a,b,d

2.b,c,d

3.c,d,a

4.a,b,c

Solution- 4.a,b,c

Reason 1-Machine translation is the process of using computer programs to translate a text/speech

from one natural language to another relevant to context. It has the ability to translate in many

languages and also required for web content and web page translation

Q:7. A brief history of Machine Translation includes:

a. Rule based Machine Translation (RBMT)

b. Example based Machine Translation (EBMT)

c. Statistical Machine Translation (SMT)

d. Neural Machine Translation (NMT)

1.a,b,c

2.c,d,a

3.a,b,c,d

4.b,c,d

Solution- 3.a,b,c,d

Reason 1-RBMT (Rule based Machine Translation) was in 1950, EBMT (Example based Machine

Translation) was in 1980, SMT was in 1990, and NMT was in 2015.

Q:8. Which of the following includes major tasks of NLP?

1.Automatic Summarization

2.Natural language understanding

3.Natural language generation

4.All the above

Solution- 1. Automatic Summarization

Reason 1- By utilizing NLP, developers can organize and structure knowledge to perform tasks such

as automatic summarization, translation, named entity recognition, relationship extraction, sentiment

analysis, speech recognition, and topic segmentation.

Q:9. Google translator is the application of

1.Machine Translation

2.Text summarization

3.Information extraction

4.None of the above

Solution- 1.Machine Translation

Reason 1- Google translator is an application of Statistical and neural machine translation

Q:10. Applications of NLP are

a. Chatbots

b. Voice assistants

c. Virtual assistant

d. None of the above

1.a,b,d

2.a,b,c

3.b,c,d

4.a,c,d

Solution- 2.a,b,c

Reason 1- All the three chatbot, virtual assistant and voice assistant are the application of NLP.

AKTU Artificial Intelligence For Engineering(KMC 101/KMC 201 )

Assignment -7

Q:1. Applications of Deep Learning are:

1.Self-driving cars

2.Fake news detection

3.Virtual Assistants

4.All the above

Solution- 4. All the above

Reason- Self-driving cars, Fake news detection and virtual assistants all are the applications of deep

learning including healthcare, fraud detection etc..

Q:2. The inputs for a single layer neural network are 1, 3, 2 and the weights of links connecting

input neurons to the output neuron are 2, 2, and 3 then the output will be (Identity activation

function is used in output neuron):

1.6

2.14

3.12

4.None of the above

Solution- 2. 14

Reason- by using this formula – Output = w1 * x1 + w2 * x2 + w3 * x3

Q:3. Which of the following is not a type of Artificial Neural Network?

1.Perceptron

2.Radial Basis Functions

3.Random Forest

4.Autoencoder

Solution- 3. Random Forest

Reason- Both the Random Forest and Neural Networks are different techniques that learn differently

but can be used in similar domains. Random Forest is a technique of Machine Learning while Neural

Networks are exclusive to Deep Learning.

Q:4. What is the limitation of deep learning?

1.Amount of data

2.Computational expensive

3.Data Labeling

4.All the above

Solution- 4. All the above

Reason- Amount of data, computational expenses and data labelling all three are the limitation of

deep learning.

Q:5. The number of nodes in the hidden layer is 8 and the output layer is 5. The maximum

number of connections from the hidden layer to the output layer are:

1.40

2.Less than 40

3.More than 40

4.It is an arbitrary value

Solution- 1. 40

Reason- it is a fully connected direct graph, the number of connections are multiple of nodes in

hidden layer and output layer.

Q:6. Recurrent Neural Networks (RNN) are used for

1.Businesses Help securities traders to generate analytic reports

2.Detecting fraudulent credit-card transaction

3.Providing a caption for images

4.All of the above

Solution- 4. All of the above

Reason- All of the above options are true. This is because RNN is used to Help securities traders to

generate analytic reports, Detecting fraudulent credit-card transaction and to provide a caption for

images.

Q:7. Types of RNN are:

1.LSTM

2.Boltzman machine

3.Hopfield network

4.a and b

Solution- 4. a and b

Reason- A Boltzmann machine (also called stochastic Hopfield network with hidden units or

Sherrington–Kirkpatrick model with external field or stochastic Ising-Lenz-Little model) is a type of

stochastic recurrent neural network. LSTM networks are a type of RNN that uses special units in

addition to standard units.

Q:8. What is perceptron?

1.a single layer feed-forward neural network with pre-processing

2.an auto-associative neural network

3.a double layer auto-associative neural network

4.a neural network that contains feedb

Solution- 1. a single layer feed-forward neural network with pre-processing

Reason- It is the simplest type of feedforward neural network , a feedforward neural network with

no hidden units. Thus, a perceptron has only an input layer and an output layer.

Q:9. Which of the following architecture has feedback connections?

1.Recurrent Neural network

2.Convolutional Neural Network

3.Restricted Boltzmann Machine

4.None of these

Solution- 2.Convolutional Neural Network

Reason- CNN is a feed forward neural network that is generally used for Image recognition and

object classification.

Q:10. Bidirectional RNN:

1.Trained to predict both the positive and negative directions of time simultaneously.

2.Applications are speech recognition, handwritten recognition etc.

3.After forward and backward passes are done, the weights are updated

4.All the above

Solution- 4. All the above

Reason- All the above options are true.

AKTU Artificial Intelligence For Engineering(KMC 101/KMC 201 )

Assignment -8

Q:1. The incorrect statement for a Convolutional Neural Network are:

1.The height and width of the filter in CNN must be less than the size of input

2.The Pooling layer progressively increases the spatial size of the representation

3.It uses both linear and non-linear activation functions

4.The last few layers are fully connected layers and computation on these layers are very time

consuming

Solution- 1.The height and width of the filter in CNN must be less than the size of input

Reason- This is because the height and width of the filter in CNN must not be less than the size of

input.

Q:2. A Convolutional Neural Network is able to successfully capture the Spatial and Temporal

dependencies:

1.True

2.False

Solution- 1.True

Reason- Yes this true, because a ConvNet is able to successfully capture the Spatial and Temporal

dependencies in an image through the application of relevant filters.

Q:3. Different types of normalization in Deep Neural Networks are

a. Output

b. Batch

c. Group

d. Instance

1.a,b,c

2.b,c,d

3.d,a,b

4.d,a,c

Solution- 2.b,c,d

Reason- Different types of normalization in Deep Neural Networks are batch, group, instance, layer,

weight etc..

Q:4. Applications of CNNs are:

a. Recommender systems

b. AlexNet

c. Natural Language Processing

d. Pooling

1.a,b

2.b,d

3.a,c

4.a,d

Solution- 4.a,d

Reason- This is because recommender system is an application of CNN and Pooling layers are used

to reduce the dimensions of the feature maps in CNN.

Q:5. Which of the following statements are correct for GAN?

a. GANs are useful for unsupervised learning, supervised learning, semi-supervised learning, and

reinforcement learning

b. Generative model technique learns to generate the data with the same statistics of training data

c. At each iteration the goal of generator is to minimize the classification error and the goal of

discriminator is to maximize the classification error.

d. The discriminator could tell the difference between images of a cat and a dog and generative model

could generate new images of animals that look like real animals.

1.a,b,c

2.a,b,d

3.a,c,d

4.b,c,d

Solution- 2.a,b,d

Reason- All the three a, b and d options are true.

Q:6. A generative model:

a. Captures the joint probability p(X,Y)

b. Captures the conditional probability p(Y|X)

c. Includes the distribution of data itself

d. Cannot predict the next word in sequence

1.a,b

2.a,c

3.a,d

4.b,c

Solution- 2. a, c

Reason- A generative model includes the distribution of the data itself, and tells you how likely a

given example is. For example, models that predict the next word in a sequence are

typically generative models (usually much simpler than GANs) because they can assign a probability

to a sequence of words. and it. It also captures the joint probability p(X,Y)

Q:7. The discriminative model:

a. Draw boundaries in the data space as it tells the difference between handwritten 0s and 1s.

b. Captures the joint probability p(X,Y)

c. Captures the conditional probability p(Y|X)

d. Learns to distinguish the generator’s fake data from real data

1.a,b,c

2.a,b,d

3.a,c,d

4.b,c,d

Solution- 3. a,c,d

Reason- The discriminative model tries to tell the difference between handwritten 0’s and

1’s by drawing a line in the data space. It captures the conditional probability p(Y|X) and Learns to

distinguish the generator’s fake data from real data

Q:8. Choose the incorrect statements from the following

1.The discriminator uses the real data as negative examples during training

2.The discriminator uses the fake data as negative examples during training

3.The portion of the GAN that trains the generator model includes random input

4.None of the above

Solution- 1.The discriminator uses the real data as negative examples during training

Reason- The generated instances become negative training examples for the discriminator. The

discriminator learns to distinguish the generator’s fake data from real data.

Q:9. Choose the correct statements from the following

a. Most universal approximation theorems can be parsed into two classes. The first quantifies the

approximation capabilities of neural networks with an arbitrary number of artificial neurons and the

second quantifies an arbitrary number of hidden layers

b. A neural network can represent any function provided it has sufficient capacity.

c. Not all architectures can represent any function

d. None of the above

1.a,b,c

2.b,c,d

3.d,a,b

4.d,a,c

Solution- 1.a,b,c

Reason- All the above options a,b and c are true. As Most of the universal approximation theorems

can be parsed into two class. The first class quantifies the approximation capabilitiesof neural

networks with an arbitrary number of artificial neurons and the second quantifies an arbitrary

numberof hidden layers

Q:10. Interesting applications of Generative Adversarial Networks (GANs) are:

1.Photo Inpainting

2.Culinary arts (as making a pizza)

3.Face aging

4.All the above

Solution- 4. All the above

Reason- Photo Inpainting, Culinary arts (as making a pizza), Face aging all are the applications of

Generative Adversarial Networks (GANs)

AKTU Artificial Intelligence For Engineering(KMC 101/KMC 201 )

Assignment -9

Q:1. Applications of face recognition system are

a. Security system

b. Attendance system

c. Smartphone’s unlocking system

d. Video surveillance system

1.a,b,c,d

2.a,b,c

3.b,c,d

4.d,a,b

Solution- 1.a,b,c,d

Reason- Attendance system, video surveillance system, Smartphone’s unlocking system and Security

system all 4 are the application of face recognition system.

Q:2. Image recognition steps are

a. Extract pixel features from an image

b. Prepare labeled images for training data

c. Train the model to be able to categorize images

d. None of the above

1.a,b,c

2.b,c,d

2.d,a,b

2.d,a,c

Solution- 1. a,b,c

Reason- All the above options a, b and c are true.

Q:3. Applications of image recognition system are

a. Driverless car technology

b. Document clustering

c. Gaming

d. All the above

1.a,b

2.b,c

3.a,c

4.c,d

Solution- 3. a, c

Reason- Developers of self-driving cars use vast amounts of data from image recognition systems,

along with machine learning and neural networks, to build systems that can drive autonomously.

The gaming arena has started using image recognition technology coupled with augmented reality to

their advantage, as it helps to provide gamers with a realistic experience.

Q:4. Object detection

a. It is a computer vision technique that allows us to identify and locate objects in an image or video

b. Object detection allows us to at once classify the types of things found while also locating instances

of them within the image

c. Draws a box around each object whereas image recognition assigns a label to an image

d. It has a capability which enables a program to process human speech into a written format

3.a,c,d

1.a,b,c

2.b,d,a

4.b,c,d

Solution- 1.a,b,c

Reason- Locate the presence of objects with a bounding box and types or classes of the located

objects in an image. It also allows us to identify and locate objects in an image or video. It allows us

to at once classify the types of things found while also locating instances of them within the image.

Q:5. Applications of object detection are

a. Video surveillance

b. Crowd counting

c. Spam/Non-spam classification

d. Self-driving cars

1.a,b,c

2.a,b,d

3.a,c,d

4.b,c,d

Solution- 2. a,b,d

Reason- Object Detection algorithms detect various types of objects for video surveillance

applications. The Nanonets API allows you to build Object Detection models with ease in crowd

counting. It is also used in self driving cars.

Q:6. Methods for object detection are

1.Viola–Jones method

2.Deep Learning approaches

3.Both (a) and (b)

4.None of the above

Solution- 3.Both (a) and (b)

Reason- The Viola–Jones object detection framework is an object detection framework which was

proposed in 2001 by Paul Viola and Michael Jones. Deep learning approach, is widely used one, for

detecting objects in images

Q:7. In which step of the processing, assigning a label (e.g., “dog”) to an object based on its

descriptors is done?

1.Object recognition

2.Morphological processing

3.Segmentation

4.Representation

Solution- 1. Object recognition

Reason- Object recognition step of the processing, assigning a label (e.g., “dog”) to an object based

on its descriptors is done

Q:8. What is the first and foremost step in Image Processing?

1.Morphological processing

2. Compression

3.Image acquisition

4.Image enhancement

Solution- 3. Image acquisition

Reason- Image acquisition is the first and foremost step in Image Processing.

Q:9. Image recognition tools are:

a. Clarifai

b. IBM Watson Visual Recognition

c. Amazon Lex

d. Scikit-image

1.a,b,c

2.b,c,d

3.a,b,d

4.d,a,c

Solution- 3.a,b,d

Reason- scikit-image is a collection of algorithms for image processing. IBM Watson Visual

Recognition is a tool that allow users to automatically identify subjects and objects contained within

the image and organize and classify these images into logical categories. By leveraging the power

of Clarifai’s image classification tools you can train your apps to recognize just about anything.

Q:10. Choose an incorrect statement

1.Image detection involves predicting the class of one object in an image.

2.Object localization refers to identifying the location of one or more objects in an image and drawing

abounding box around their extent

3.Object detection combines these two tasks and localizes and classifies one or more objects in an

image

4.Detection is the process of identification and classification is the categorization of the object based

on a previously defined classes or types

Solution- 2. Object localization refers to identifying the location of one or more objects in an

image and drawing abounding box around their extent

Reason- All the above are correct except the second one.

AKTU Artificial Intelligence For Engineering(KMC 101/KMC 201 )

Assignment -10

Q:1. Choose the incorrect statement:

1.Speech recognition is a way of encoding and decoding analog signals

2.Differently abled people can use speech recognition system.

3.The first speech recognition systems were focused on numbers not words

4.None of the above

Solution- 4. None of the above

Reason- This is because speech recognition is a way of encoding and decoding analog signals, and it

can be used for Differently abled people. The first speech recognition systems were focused on

numbers, not words. In 1952, Bell Laboratories designed the “Audrey” system which could

recognize a single voice speaking digits aloud.

Q:2. Voice search engines are:

a. Google Assistant

b. Siri

c. Alexa

d. Cortana

1.a,b,c,d

2.b,c,d

2.d,a,b

2.d,a,c

Solution- 1. a,b,c,d

Reason- All the four are voice search engines given in the options

Q:3. Types of speech recognition systems

1.Speaker independent

2.Speaker dependent

3.Speaker adaptive

4.All the above

Solution- 4. All the above

Reason- if speaker-dependent data are available, the system could be adapted to the

specific speaker such that the error rate could be significantly reduced. Speaker–

dependent software is commonly used for dictation software, while speaker–independent software is

more commonly found in telephone applications.

Q:4. Steps of speech recognition system include

a. Analog to digital conversion

b. Wavelets and multiresolution processing

c. Use of acoustic and language model

d. Segmentation

1.a,b

2.b,c

3.c,a

4.a,d

Solution- 4. a,d

Reason- First, the speech is analyzed to determine the likely locations of phoneme boundaries;

second, the segments that result from this analysis are classified based on features taken from

throughout the segment

Q:5. Applications of speech recognition systems are

a. Home automation

b. Voice dialing

c. Color processing

d. Translation

1.a,b,c

2.a,b,d

3.a,c,d

4.b,c,d

Solution- 2.a,b,d

Reason- Speech recognition applications include voice user interfaces such as voice dialing (e.g.

“call home”), call routing (e.g. “I would like to make a collect call”) and translation.

Q:6. In computer vision

a. The tasks include methods for acquiring, processing, analyzing and understanding digital images

b. Most computer vision systems rely on image sensors, which detect electromagnetic radiation,

which is typically in the form of either visible or infra-red light

c. The working of visual cortex of a dog has introduced the concept of edge detection.

d. All the above

1.a,b

2.b,c

3.c,d

4.a,d

Solution- 1.a,b

Reason- The option a and b are true because computer vision tasks include methods for acquiring,

processing, analyzing and understanding digital images and most computer vision systems rely on

image sensors, which detect electromagnetic radiation, which is typically in the form of either visible

or infra-red light

Q:7. How computer vision works

a. Acquiring an image

b. Processing the image

c. Analyzing the image

d. Understanding the image

1.a,b,c,d

2.a,b,c

3.d,a,b

4.d,a,c

Solution- 1. a,b,c,d

Reason- Computer vision tasks include methods for acquiring, processing, analyzing and

understanding digital images, and extraction of high-dimensional data from the real world in order to

produce numerical or symbolic information

Q:8. Potential application areas of robots

a. Military robots

b. Drones

c. Medical robot

d. None of the above

1.a,b,c

2.b,c,d

3.a,b,d

4.d,a,c

Solution- 1.a,b,c

Reason- All of the above options are the potential applications of robots.

Q:9. Artificial Intelligence techniques can

a. Analyze large amount of data

b. Take complicated decision easily

c. Replace humans in near future from almost all type of jobs

d. Be used in Logistic and Supply chain management

1.a,b,c

2.b,c,d

3.a,b,d

4.d,a,c

Solution- 3.a,b,d

Reason- This is because experts are confident that artificial intelligence will operate hand in hand

with humans in the workplace, not take their jobs.

Q:10. How a robot works?

1.Uses pre-programmed instructions stored in CPU

2.It need special hardware with sensors and effectors

3.Robot sensors send feedback to controllers

4.All the above

Solution- 4.All the above

Reason- All the above options are true because robots uses some programs and it need special

hardware with sensors and effectors and these robot sensors send feedback to controllers.

27. ________ refers to the basic principles of AI system design that use the good code of conduct

and produces the results.

Ethics

AI ethics

Morals

AI- Morals

None

Ans: b

28. The world of AI revolves around ___________

a. code

b. algorithms

c. data

d. computer

e. None of the above

FOR IMPORTANT NOTES TOUCH TO "!! ADITYA !!"

Ans: c

29. Amazon used a system for recruitment, created a situation in which many eligible females

were left out of the consideration. This is called _________.

a. Misinterpretation of Data

b. Problem of security

c. Gender Bias

d. Data Privacy

e. None of the above

Ans: c

30. Which of the following chatbot launched by Microsoft as an experimental Twitter chatbot?

Twitterbot

TwiChatBot

Tay

TwitterRobo

None of the above

Ans: c

FOR IMPORTANT NOTES TOUCH TO "!! ADITYA !!"

MCQ

UNIT-II

1. Which of the following refers to the problem of finding abstracted patterns (or structures) in

the unlabeled data?

a)Supervised learning

b)Unsupervised learning

c)Hybrid learning

d)Reinforcement learning

e) None of the above

Ans : b

2. Which one of the following refers to querying the unstructured textual data?

a. Information access

b. Information update

c. Information retrieval

d. Information manipulation

e. None of the above

Ans : c

3. The following given statement can be considered as the examples of_________

Suppose one wants to predict the number of newborns according to the size of storks' population

by performing supervised learning

a) Structural equation modeling

b) Clustering

c) Regression

d) Classification

e) None of the above

Ans : c

4. Which of the following statement is true about the classification?

a) It is a measure of accuracy

b) It is a subdivision of a set

c) It is the task of assigning a classification

d) All of the above

e) None of the above

Ans : b

5. Which one of the following can be defined as the data object which does not comply with the

general behavior (or the model of available data)?

a) Evaluation Analysis

b) Outliner Analysis

c) Classification

d) Prediction

e) None of the above

Ans : b

6. Which one of the following statements is not correct about the data cleaning?

a) It refers to the process of data cleaning

b) It refers to the transformation of wrong data into correct data

c) It refers to correcting inconsistent data

d) All of the above

e) None of the above

Ans : d

7. Which one of the following correctly defines the term cluster?

a) Group of similar objects that differ significantly from other objects

b) Symbolic representation of facts or ideas from which information can potentially be

extracted

c) Operations on a database to transform or simplify data in order to prepare it for a machinelearning algorithm

d) All of the above

e) None of the above

Ans : a

8. Which one of the following refers to the binary attribute?

a) This takes only two values. In general, these values will be 0 and 1, and they can be coded

as one bit

b) The natural environment of a certain species

c) Systems that can be used without knowledge of internal operations

d) All of the above

e) None of the above

Ans : a

9. Which is not a category of data?

a) numerical data

b) categorical data

c) time-series data

d) text

e) none of these

Ans : e

10. Which is incorrect about categorical data

a) categorical data represents characteristics, such as a hockey player’s position, team,

hometown

b) Categorical data can take numerical values.

c) Both a and b

d) Only a

e) None of the above

Ans : c

11. Identify the incorrect statement about data.

a) Primary data — Data that you create yourself

b) Secondary data — Data that you collect from someone else

c) Primary data example-Google analytics report on your website traffic.

d) Secondary data example-Interviewing people in your organization.

e) None of the above

Ans : b, c

12. Which is not a type of data storage?

a) Software-defined storage and File storage

b) Cloud storage and Block storage

c) Network-attached storage and Object storage

d) All of the above

e) None of the above

Ans : d

13. Advantages of DAQ are

a) Improves the efficiency and reliability of processes or machinery

b) Decrease update errors

c) Data entry, storage and retrieval costs are reduced

d) Supervision of processes without human interaction

e) None of the above

Ans : a, b, c, d

14. Why Data Preprocessing is required

a) Data is Incomplete

b) Data is Noisy

c) Data is inconsistent

d) All of the above

e) None of the above

Ans : d

15. Which is not a stage of data processing

a. Data collection

b. Data preparation

c. Data input

d. Processing

e. None of the above

Ans : e

16. Which statement is incorrect regarding data visualization.

a) To make easier in understand and remember.

b) To discover unknown facts, outliers, and trends.

c) To visualize relationships and patterns quickly.

d) To improve insights.

e) None of the above

Ans : e

17. Which of the following is not a data visualization tool?

a) Tableau

b) Infogram

c) Chartblocks

d) Datawrapper

e) None of the above

Ans : e

18. A good recommender

a) Show programming titles to a software engineer and baby toys to a new mother.

b) Don’t recommend items user already knows or would find anyway.

c) Expand user’s taste without offending or annoying him/her

d) All of the above

e) None of the above

Ans : d

19. Which statement is incorrect regarding challenge of recommender system.

a) Huge amounts of data, tens of millions of customers and millions of distinct catalog

items.

b)Results are required to be returned in real time.

c)New customers have limited information.

d)Customer data is non volatile.

e)None of the above

Ans : d

20. Which is incorrect regarding data processing?

a) Data processing occurs when data is collected and translated into usable information.

b) Data processing starts with data in its meaningful form.

c) Usually performed by a data scientist or team of data scientists

d) It is important for data processing to be done correctly as not to negatively affect the

end product or data output.

e) None of the above

Ans : b

21. Identify the correct statement regarding Data collection.

a) First step in data processing

b) Data is pulled from available sources, including data lakes and data warehouses.

c) Raw data is diligently checked for any errors

d) All of the above

e) None of the above

Ans : a, b

22. Data output/interpretation is

a) The stage at which data is finally usable to non-data scientists.

b) It is translated, readable, and often in the form of graphs, videos, images.

c) Members of the company or institution can now begin to self-serve the data for their

own data analytics projects.

d) All of the above

e) None of the above

Ans : d

23. Select the correct statement

a) The first stage of data processing is storage .

b) When data is properly stored, it can be quickly and easily accessed by members of the

organization when needed.

c) Data input is the last stage in which raw data begins to take the form of usable

information.

d) Once the data is collected, it then enters the data preparation stage.

e) None of the above

Ans : a, c

24. Identify the incorrect statement.

a) Categorical data data is a sequence of numbers collected at regular intervals over some

period of time.

b) Text data is basically just words.

c) Time series represents characteristics, such as a hockey player’s position, team, and

hometown.

d) All of the above

e) None of the above

Ans : a, c

25. Which is correct about Numerical Data

a) Numerical data is any data where data points are exact numbers.

b) Statisticians also might call numerical data as quantitative data.

c) Example of numerical data: residential properties in Los Angeles or how many houses

sold in the past year.

d) All of the above

e) None of the above

Ans : d

26. Which is incorrect about data visualization.

a) Data visualization is a graphical representation of quantitative information and data by

using visual elements like graphs, charts, and maps.

b) Data visualization convert large and small data sets into visuals, which is easy to

understand and process for humans.

c) Data visualization tools provide accessible ways to understand outliers, patterns, and trends

in the data.

d) a and c

e) None of the above

Ans : a, b, c

27. Point the incorrect statement about area chart

a) This visualization method is a variation of a line chart

b) Takes the form of an x- and y-axis with dots to represent data points

c) This method shows hierarchical data in a nested format

d) It displays multiple values in a time series

e) None of the above

Ans : b, c

28. Find the correct statement about File storage system.

a) File storage arranges data as hierarchical files that users can open and navigate from

top to bottom.

b) Files are stored on back ends and front ends

c) File storage splits storage volumes into individual instances known as blocks

d) File storage breaks data into discrete units and pairs them with metadata to provide

context about what’s contained within it

e) None of the above

Ans : a, b

29. A data acquisition system consists of which of the following elements:

a) Sensor

b) Signal conditioner

c) Analog to digital signal converter

d) All of the above

e) None of the above

Ans : d

30. identify the incorrect statement.

a) Sensor is a device, also known as a transducer, capable of transforming conditions of

reality, such as temperature or motion, into an electrical signal that can be measured and

analysed with a computer.

b) Signal conditioner: It is the key to any data acquisition process. It is a chip that transforms

the signal captured from reality into information that can be interpreted by a processor.

c) Analog to digital signal converter: This is a device that filters the analog signal picked up

by sensors before converting it into digital information.

d) All of the above

e) None of the above

Ans : b, c

MCQ

UNIT-III

1) Bell labs introduced which system

a) Audrey

b) Shoebox

c) IBM machine

d) Sophia

e) none of the above

ans: a

2) speech recognition is also known as

a) automatic speech recognition

b) computer speech recognition

c) speech to text

d) all of the above

e) none of the above

ans: d

3) speech recognition applications are

a) Alexa

b) Siri

c) chatbot

d) all of the above

e) none of the above

ans: a,b

4) speech recognition can understand speech but can’t understand

a) emotions

b) text

c) speech

d) all of the above

e) none of the above

ans: a

5) components in working mechanism of speech recognition are

a) acoustic model

b) digital to analog

c) voice engine

d) all of the above

e) none of the above

ans: a

6) speech recognition stages are

a) analysis

b) modeling and feature extraction

c) both a and b

d) voice modulation

e) none of the above

ans: c

7) what is NLU

a) natural language undertaken

b) natural language understanding

c) natural language uniform

d) natural language universe

e) none of these

ans: b

8) NLU is a subfield of

a) AI

b) ML

c) NLP

d) Deep learning

e) none of these

ans: a

9) NLU is used in

a) classification

b) language detection

c) sentiment analysis

d) all of the above

e) none of the above

ans: d

10) what is NLG

a) natural language generation

b) natural language genetics

c) natural language gap

d) all of the above

d) none of the above

ans: a

11) NLG is a subfield of

a) AI

b) NLP

c) ML

d) NLU

e) none of these

ans: a

12) NLP=x+y

a) x= NLG, y=NLU

b) x= ML, y=AI

c) x= NLG, y= AI

d) x= AI, y =DL

e) none of these

ans: a

13) chatbot is an AI based computer program that simulates

a) human conversation

b) chatting

c) speech recognition

d) voice recognition

e) none of the above

ans: a

14) types of chatbot

a) rule based chatbot

b) conversational chatbot

c) both a and b

d) speech chatbot

e) none of the above

ans: c

15) what is machine translation

a) translates text from one language to another

b) translates speech from one language to another

c) translates voice from one language to another

d) all of these

e) none of the above

ans: a and b

16) Inshorts application is an application of

a) NLG

b) NLU

c) ML

d) AI

e) none of the above

ans: a

17) Shoebox machine was invented in

a) 1960

b) 1962

c) 1965

d) 1966

e) none of the above

ans: b

18) challenges in speech recognition

a) bad recording equipment

b) background noise

c) difficult accents and dialects

d) all of the above

e) none of these

ans: d

19) Applications of NLP

a) Speech recognition

b) Google maps

c) chatbot

d) all of the above

e) none of the above

ans: d

20) chatbot reduces

a) business growth

b) customer churn rate

c) one to one interaction

d) none of the above

e) all of the above

ans: b

21) speech recognition application are

a) wearables

b) telephony

c) military

d) all of the above

e) none of the above

ans: d

22) sentiment analysis is an application of

a) NLU

b) NLG

c) ML

d) all of the above

e) none of the above

ans: a

23) topic classification is an application of

a) NLU

b) NLG

c) ML

d) AI

e) none of these

ans: a

24) importance of chatbot

a) reduce customer waiting time

b) better customer engagement

c) 24*7 availability

d) all of the above

e) none of the above

ans: d

25) types of chatbots are:

a) rule based chatbot

b) conversational chatbot

c) both a and b

d) speech chatbot

e) none of the above

ans: c

26) chatbot is an AI based computer program that simulates

a) human conversation

b) chatting

c) speech recognition

d) voice recognition

e) none of the above

ans: a

27) NLG is a subfield of

a) AI

b) NLP

c) ML

d) NLU

e) none of these

ans: a

28) machine translation applications:

a) government

b) enterprise

c) social

d) all of the above

e) none of the above

ans: d

29) question and answering is an application of:

a) NLP

b) AI

c) ML

d) all of the above

e) none of the above

ans: a

30) machine translation is difficult because of the following:

a) ambiguity

b) word order

c) phrases

d) all of the above

e) none of the above

ans: a and b

UNIT-4

MCQ

1. Applications of Deep Learning are:

Self-driving cars

Fake news detection

Virtual Assistants

All the above

None of these

Ans: d

2. Which of the following is not a type of Artificial Neural Network?

Perceptron

Radial Basis Functions

Random Forest

Autoencoder

None of these

Ans: c

3. What is the limitation of deep learning?

Amount of data

Computational expensive

Data Labeling

All the above

None of these

Ans: d

4. Recurrent Neural Networks (RNN) are used for

Businesses Help securities traders to generate analytic reports

Detecting fraudulent credit-card transaction

Providing a caption for images

All of the above

None of these

Ans: d

5. Types of RNN are:

LSTM

Boltzman machine

Hopfield network

a and b

None of these

Ans: d

6. What is Perceptron?

a)a single layer feed-forward neural network with pre-processing

b)an auto-associative neural network

c)a double layer auto-associative neural network

d)a neural network that contains feedb

e)None of these

Ans: a

7. Which of the following architecture has feedback connections?

Ans: b

Recurrent Neural network

Convolutional Neural Network

Restricted Boltzmann Machine

Multilayer Feed Forward Neural Network

None of these

Ans: d

Trained to predict both the positive and negative directions of time simultaneously.

Applications are speech recognition, handwritten recognition etc.

After forward and backward passes are done, the weights are updated

All the above

None of these

Bidirectional RNN:

Which of the following deep learning models uses back propagation?

a) Convolutional Neural Network

b) Multi Layer Perceptron Network

c) Recurrent Neural Network

d) Support Vector Machine

e) None of these

Ans: c

10. The incorrect statement for a Convolutional Neural Network are:

The height and width of the filter in CNN must be less than the size of input

The Pooling layer progressively increases the spatial size of the representation

It uses both linear and non-linear activation functions

The last few layers are fully connected layers and computation on these layers are very

time consuming

e) None of these

Ans: a

11. A Convolutional Neural Network is able to successfully capture the Spatial and Temporal

dependencies:

True

False

Partially Correct

Depends on Category of Problem

None of these

Ans: a

12. Different types of normalization in Deep Neural Networks are:

a) Output

b) Batch

c) Group

d) Instance

e) None of these

Ans: b, c, d

13. Applications of CNNs are:

a) Recommender systems

b) AlexNet

c) Natural Language Processing

d) Pooling

e) None of these

Ans: a, d

14. Which of the following statements are correct for GAN?

a) GANs are useful for unsupervised learning, supervised learning, semi-supervised

learning, and reinforcement learning

b) Generative model technique learns to generate the data with the same statistics of training

data

c) At each iteration the goal of generator is to minimize the classification error and the goal

of discriminator is to maximize the classification error.

d) The discriminator could tell the difference between images of a cat and a dog and

generative model could generate new images of animals that look like real animals.

e) None of these

Ans: a, b, d

15. A generative model:

a) Captures the joint probability p(X,Y)

b) Captures the conditional probability p(Y|X)

c) Includes the distribution of data itself

d) Cannot predict the next word in sequence

e) None of these

Ans: a, c

16. The discriminative model:

a) Draw boundaries in the data space as it tells the difference between handwritten 0s and

1s.

b) Captures the joint probability p(X,Y)

c) Captures the conditional probability p(Y|X)

d) Learns to distinguish the generator’s fake data from real data

e) None of these

Ans: a, c, d

17. Choose the incorrect statements from the following

Ans: a

The discriminator uses the real data as negative examples during training

The discriminator uses the fake data as negative examples during training

The portion of the GAN that trains the generator model includes random input

The discriminator uses fake data during training

None of the above

18. Choose the correct statements from the following

a) Most universal approximation theorems can be parsed into two classes. The first

quantifies the approximation capabilities of neural networks with an arbitrary number of

artificial neurons and the second quantifies an arbitrary number of hidden layers

b) A neural network can represent any function provided it has sufficient capacity.

c) Not all architectures can represent any function

d) None of the above

Ans: a, b, c

19. Interesting applications of Generative Adversarial Networks (GANs) are:

Ans: d

Photo Inpainting

Culinary arts (as making a pizza)

Face aging

All the above

None of these

20. Why is an RNN (Recurrent Neural Network) used for machine translation, say

translating English to French? (Check all that apply.)

a) It can be trained as a supervised learning problem.

b) It is strictly more powerful than a Convolutional Neural Network (CNN).

c) It is applicable when the input/output is a sequence (e.g., a sequence of words).

d) RNNs represent the recurrent process of Idea->Code->Experiment->Idea->....

e) None of these

Ans: a , c

21. Typically how many layers are in CNN

a) 2

b) 3

c) 5

d) 6

e) None of these

Ans: b

22. Pooling is responsible for:

a) Reducing the size of filter layer

b) Prevents Overfitting

c) Prevents Underfitting

d) Reduce the training time

e) None of these

Ans: a, b

23. Re-Lu refers to

a) Activation function

b) Transfer Function

c) Error Function

d) Optimization function

e) None of these

Ans: a

24. Re-Lu will only returns value if the value is greater than:

a) 0

b) 1

c) -1

d) 2

e) None of these

Ans: a

25. Which of the following statement is/are correct about CNN

a) Every neurons shares a connection with all others neurons in the layer before

b) Every neurons shares a connection with all others neurons in the layer after

c) Every neurons shares a connection with only few neurons in the layer before

d) Every neurons shares a connection with only few neurons in the layer after

e) None of these

Ans: a,b

26. Which of the following statement is not correct?

a) Neural Network mimic the human brain

b) It can only work for single input and single output

c) It can be used in image processing

d) It can be used in classification problems

e) None of these

Ans: b

27. Neural Networks can be used in:

a) Regression Problems

b) Classification problems

c) Clustering Problems

d) Prediction problem

e) None of these

Ans: b, c

28. UAT in AI stand for:

a) Universal Approximation Theorem

b) Universal Acceptance Theorem

c) Universal Acceptance Testing

d) Unified Acceptance Theorem

e) None of these

Ans: a

29. GAN stands for:

a) Generative Adoptive Network

b) Generative Adversial Network

c) Genuine Adoptive Neurons

d) Genuine Adversial Neurons

e) None of these

Ans: b

30. What are the sub-models of GAN?

a) Generator

b) Discriminator

c) Adopter

d) Classifier

e) None of these

Ans: a, b

UNIT 5

MCQ

1. What enables people to recognize people, animals and inanimate objects reliably?

a) Speech

b) Vision

c) Hear

d) Perception

e) None of the above

ANS: b

2. Which are recognized by vision?

a) Objects

b) Activities

c) Motion

d) Both Objects & Activities

e) None of the above

ANS: d

3. How many types of recognition are there in artificial intelligence?

a) 1

b) 2

c) 3

d) 4

e) None of the above

ANS: c

4. Which provides a framework for studying object recognition?

a) Learning

b) Unsupervised learning

c) Supervised learning

d) All of the above

e) None of the above

ANS: c

5. Which object recognition process is an error-prone process?

a) Bottom-up segmentation

b) Top-down segmentation

c) Both Bottom-up & Top-down segmentation

d) All of the above

e) None of the above

ANS: a

6. What can be represented by using histograms or empirical frequency distributions?

a) Words

b) Color

c) Texture

d) Both Color & Texture

e) None of the above

ANS: d

7. Which is the only way to learn about the different kinds of human faces?

a) Perception

b) Speech

c) Learning

d) Hearing

e) None of the above

ANS: c

8. The signal that is used in speech recognition is known as?

a) Acoustic signal

b) Electric signal

c) Electromagnetic signal

d) Radar

e) None of the above

ANS: c

9. Which is known as the properties of the signal that extend over interval?

a) Hops

b) Rate

c) Frames

d) All of the above

e) None of the above

ANS: c

10.Which of the following model provides the probability of every word following every other

word?

a) Gram model

b) Diagram model

c) Bigram model

d) Speech model

e) None of the above

ANS: c

11.Which specifies the prior probability of every utterance?

a) Sound model

b) Language model

c) Model

d) All of the above

e) None of the above

ANS: b

12.Which of the following effects are partially captured by the triphone model?

a) Coarticulation effects

b) Articulation effects

c) Both Articulation and Coarticulation effects

d) context-dependent effect

e) None of the above

ANS: a

13.Select the dominant modality for communication between humans?

a) Hear

b) Speech

c) Smell

d) Touch

e) None of the above

ANS: b

14.Select the periodic changes in pressure that propagate through the air?

a) Airwaves

b) Sound waves

c) Rate

d) Signal waves

e) None of the above

ANS: b

15.The study of how language sounds are called?

a) Phonology

b) Biology

c) Trilogy

d) Speechology

e) None of the above

ANS: a

16.Which is considered as a problem of probabilistic inference?

a) Utterance

b) Speaking

c) Hearing

d) Speech recognition

e) None of the above

ANS: d

17. What is the name for information sent from robot sensors to robot controllers?

a) temperature

b) pressure

c) feedback

d) signal

e) None of the above

ANS: c

18.Which of the following terms refers to the rotational motion of a robot arm?

a) swivel

b) axle

c) retrograde

FOR IMPORTANT NOTES TOUCH TO "!! ADITYA !!"

STUDY ZONE

d) roll

e) None of the above

ANS: d

19. What is the name for space inside which a robot unit operates?

a) environment

b) spatial base

c) work envelope

d) exclusion zone

e) None of the above

ANS: c

20. Which of the following terms IS NOT one of the five basic parts of a robot?

a) peripheral tools

b) end effectors

c) controller

d) drive

e) None of the above

ANS: a

21. Which of the following is application domains of Computer Vision?

a) Agriculture

b) Biometrics

c) Page control

d) Transport

e) None of the above

ANS: a, b, d

22. Which of the following statements concerning the implementation of robotic systems is

correct?

a) implementation of robots CAN save existing jobs

b) implementation of robots CAN destroy new jobs

c) robotics could prevent a business from closing

d) All of the above

e) None of the above

ANS: a, c

23. The number of moveable joints in the base, the arm, and the end effectors of the robot

determines_________

a) degrees of freedom

b) payload capacity

c) operational limits

d) flexibility

e) None of the above

ANS: a

24. Which of the following places would be LEAST likely to include operational robots?

a) warehouse

b) factory

c) hospitals

d) private homes

e) None of the above

ANS: d

25. For a robot unit to be considered a functional industrial robot, typically, how many degrees

of freedom would the robot have?

a) three

b) four

c) six

d) eight

e) None of the above

ANS: c

26. Which of the basic parts of a robot unit would include the computer circuitry that could be

programmed to determine what the robot would do?

a) sensor

b) controller

c) arm

d) end effector

e) None of the above

ANS: b

27. The transition between continuous values of the image function and its digital equivalent is

called ______________

a) Quantization

b) Sampling

c) Rasterization

d) frequency

d) None of the above

ANS: a

28. What is the tool used in tasks such as zooming, shrinking, rotating, etc.?

a) Sampling

b) Interpolation

c) Filters

d) All of the above

e) None of the above

ANS: b

29. Dynamic range of imaging system is a ratio where the upper limit is determined by

a) Saturation

b) Noise

c) Brightness

d) Contrast

e) None of the above

ANS: a

30. Which of the following is an application of AI?

a) Gaming

b) Expert Systems

c) Speech Recognition

d) Content mining

e) None of the above

Ans: a, b, c

ABES ENGINEERING COLLEGE, Ghaziabad.

Department of Applied Science

Unit-1 (Multiple Choice Questions)

40 Mcqs Based Questions with answers:

1. What is Artificial intelligence?

Putting your intelligence into Computer

Programming with your own intelligence

Making a Machine intelligent

Playing a Game

Putting more memory into Computer

2. The name Prolog, is short for ___

Programming In Logic

Programming logic

Practical logic

Pattern logic

3. Artificial Intelligence (AI) is one of the newest disciplines, formally initiated in ___

the name was coined.

1943

1924

2000

1996

4. Who proposed Turing test??

Alan Turing

Jhon Turing

Elan Turing

None of the above

5. The major components required for AI:

knowledge representation

reasoning

language/image understanding and learning

All of the above

6. What was originally called the “imitation game” by its creator?

a. The Turing Test

b. LISP

c. The Logic Theorist

d. Cybernetics

7. Which of the following are comprised within AI?

Machine Learning

Deep Learning

Both (1) and (2)

None of the above

8. "Artificial Intelligence means to mimic a human. Hence, if a robot can move from one place to

another like a human, then it comes under Artificial Intelligence."

a. True

b. False

9. Which of the mentioned human behavior does the AI aim to mimic?

Thinking

Eating

Sleeping

None of the above

10. Strong Artificial Intelligence is __________

An AI system with generalized human cognitive abilities.

Also called as narrow AI.

All actions are preprogramed by human

None of the above

11. A certain Professor at the Stanford University coined the word ‘artificial intelligence’ in

1956 at a conference held at Dartmouth college. Can you name the Professor?

David Levy

John McCarthy

Joseph Weizen

baum

Hans Berliner

12. Which of the following could be the approaches to Artificial Intelligence?

Strong Artificial Intelligence

Weak Artificial Intelligence

Applied Artificial Intelligence

All of the mentioned

13. DARPA, the agency that has funded a great deal of American Artificial Intelligence research,

is part of the Department of

a. Defense

b. Energy

c. Education

d Justice

14. Which of the following is not an application of AI?

Pattern recognition

Crop prediction

Digital assistant

Fund transfer

15. Weak AI is

a. A set of computer programs that produce output that would be considered to reflect

intelligence if it were generated by humans.

b. Useful for testing hypothesis about minds, but would not actually be minds

c. The embodiment of human intellectual capabilities within a computer.

d. None of the above

16. What are the main goals of AI?

a. Create Expert Systems

b. Implement Human Intelligence in Machines

c. Both Options

d. None of the above

17. The characteristics of the computer system capable of thinking, reasoning and learning is

known is

machine intelligence

human intelligence

artificial intelligence

virtual intelligence

18. Natural Language Processing is divided into

Numeric and Symbolic

Understanding and Generation

Inference and Deduction

Conclusion and Generation

19. The network that involves backward links from output to the input and hidden layers is called

a. Self-organizing maps

b. Recurrent neural network

20. What is back propagation?

a. It is another name given to the curvy function in the perceptron

b. It is the transmission of error back through the network to adjust the inputs

c. It is the transmission of error back through the network to allow weights to be

adjusted so that the network can learn

21. Machines that can do things like speech recognition, visual perception, and decision making

are said to have what?

Artificial intelligence

Machine Programming

Machine learning

Programmable Memory

22. Artificial Intelligence has its expansion in the following application.

Search engines

Gaming

Robotics

All of the above

23 PROLOG is an AI programming language which solves problems with a form of symbolic

logic known as predicate calculus. It was developed in 1972 at the University of Marseilles by a

team of specialists. Can you name the person who headed this team?

Alain Colmerauer

Nicklaus Wirth

Seymour Paper

John McCarthy

24. Which of the following is not a branch of Artificial Intelligence?

Expert systems

Robotics

Natural language Processing

None of the above

25. What of the following is considered to be a pivotal event in the history of AI.

1949, Donald O, The organization of Behavior.

1950, Computing Machinery and Intelligence.

1956, Dartmouth University Conference Organized by John McCarthy

1961, Computer and Computer Sense.

26. Which of the following is not an application of Unsupervised Learning

Document clustering

Speech recognition

Image compression

Association analysis

27. The technology that has the ability to interact with the world.

IOT

28. Face recognition system is based on _____________

applied AI

parallel AI

serial AI

strong AI

29. Which of the following areas can contribute to build an intelligent system?

Philosophy

Biology

Sociology

All of the above

30. Blanket Surveillance is….

An ethical concern

A Machine learning algorithm

A speech recognition technique

None of the above

31. Natural Language Processing (NLP) is field of

Computer Science

Artificial Intelligence

Linguistics

All of the mentioned

32. What are roles in AI career?

a. Software analysts and developers

b. Computer scientists and computer engineers

c. Algorithm specialists

d. All of the above

33.Basic unit of neural network?

a. neuron

b. node value

c. Bayes Nets

d. All of the above

34 .AI vs . Human Brain

a. Humans use content memory and thinking whereas, robots are using built-in instructions,

b. Artificial intelligence cannot beat human intelligence at all

c. The field of Artificial intelligence limits on designing machines that can mimic

human behavior.

d. None of the above

35. The concept of artificial neurons was introduced in which year ?

a. 1940

b. 1943

c. 1950

d. 1955

36. Ethical issues with AI are?

Privacy & Surveillance

Bias in Decision Systems

Automation & Employment

All of the above

37. The first Humanoid Robot was built-in which year?

1950

1965

1972

1987

38. Which of the following is not a stage of AI?

Cognitive analytics

Predictive analytics

Diagnostic analytics

None of the above

39. Which part of artificial intelligence is concerned with AI agents that think and how thinking

contributes to intelligent behavior of agents?

A. Knowledge representation and reasoning (KRR)

B. Robotics

C. Information and Data

D. Problem Solving

40. ML is the learning in which machine can learn on its own without being ___ programmed.

a. Implicitly

b. Explicitly

ABES Engineering College, Ghaziabad

Department of Applied Science

Unit-2 (Multiple Choice Questions)

1. Data Visualization is:

a. Used to communicate information clearly and efficiently to users by the usage of

information graphics such as tables and charts.

b. Helps users in analyzing a large amount of data in a simpler way.

c. Makes complex data more accessible, understandable, and usable.

d. All of the above

2. Data Visualization tool that can be used for displaying hierarchical data:

Histogram

Tree map

Scatter plot

Pie chart

3. Which of the following is a Regression problem?

Weather forecasting

Spam/Not-Spam emails categorization

Sentiment analysis

Fraud detection

4. Which of the following is a Classification problem?

Estimating the price of house

Credit/loan approval

Recommender system

Predicts the number of items which a consumer will probably purchase

5. Decision tree:

a. Belongs to a family of unsupervised learning algorithms

b. Consider all attributes to split at each node, starting from the root node

c. Create a model that can be used to predict the class or value of the target variable

by learning simple decision rules inferred from training data

d. All the above

Solution- 3. Create a model that can be used to predict the class or value of the

target variable by learning simple decision rules inferred from training data

Reason 1- because it is used to create a model that can be used to predict the class or

value of the target variable by learning simple decision rules inferred from training data

Reason 2- because it’s wont to create a model which will be wont to predict the category

or value of the target variable by learning simple decision rules inferred from training

data

6. Bayesian Classifier:

Connects the degree of belief in a hypothesis before and after accounting for evidence

Uses conditional and marginal probability

Performance can be estimated using accuracy, precision, recall

All the above

7. When two clusters have a parent-child relationship then it is called as:

K-means clustering

Fuzzy c-means clustering

Hierarchical clustering

Density based clustering

8. Recommender system is an example of:

Clustering

Supervised learning

Reinforcement learning

Regression

9. Mnist Digit Recognition is an example of:

Regression

Classification

Data Mining

Data Science

10. Classifying Species of a flower Dataset can be achieved using which type of machine

learning algorithm

a. Supervised Machine Learning

b. Unsupervised Machine Learning

c. Reinforcement Learning

11. Face Recognition is an example of which concepts:

a. Computer vision

b. Classification

FOR IMPORTANT NOTES TOUCH TO "!! ADITYA !!"

STUDY ZONE

c. None of the above

d. Both of them

12. Which of the following process does not belong to steps of Machine Learning Pipeline??

Data Collection

Data Preprocessing

Model Building

None of the above.

13. Unsupervised Learning algorithms can be applied to

a. Clustering

b. Association

c. All of the above

14. Which of the following evaluation metrics used for Classification Projects??

Precision

Recall

Accuracy

All of the above

15.In Confusion Matrix What are the parameters are there??

True Positive

False Positive

False Negative

True Negative

All of the above

16. A regression model is one in which more than one independent variable is used to predict the

dependent variable is called??

Simple Linear Regression

Multiple Linear Regression

an Independent Model

None of the above

17. What is Machine learning?

a) The autonomous acquisition of knowledge through the use of computer programs

b) The autonomous acquisition of knowledge through the use of manual programs

c) The selective acquisition of knowledge through the use of computer programs

d) The selective acquisition of knowledge through the use of manual programs

18. Data Visualization can be achieved by which Python Libraries??

Sea born

Matplotlib

Plotly

Tensorflow

Keras

Seaborn, Matplotlib, Plotly

19. Classification Problems are distinguished from estimation problems in that

Classifcation requires the output attribute in numeric.

Classification requires the output attribute is Categorical.

Classification does not allow an output attribute.

Classification Problems do not require the Future outcome.

20. Simple Regression assumes a--------------- Relationship between the input attribute and the

Output Attribute:

Linear

Quadratic

Elliptical

None of the above

21. DIKW:

1.Stands for Data, Information, Knowledge, Wisdom

2.In 1994 Nathan Shedroff presented the DIKW hierarchy in an information design context

3.In this context data is considered as symbols representing signals

4.All the above statements are correct

Solution- 1.Stands for Data, Information, Knowledge, Wisdom

Reason 1- Knowledge Pyramid, Wisdom Hierarchy and Information Hierarchy are some of the

names referring to the popular representation of the relationships between data, information,

knowledge and wisdom in the Data, Information, Knowledge, Wisdom (DIKW) Pyramid.

Reason 2- Knowledge Pyramid, Wisdom Hierarchy and knowledge Hierarchy are a number of

the names pertaining to the favored representation of the relationships between data, information,

knowledge and wisdom within the Data, Information, Knowledge, Wisdom (DIKW) Pyramid.

22. How many types of Machine Learning are there?

23. Supervised Machine Learning have………………………………………. In order to train

the model.

a. Labelled data

b. Unlabeled Data

24. The field that investigates the human the mechanics of Human Intelligence

Cognitive Science

Sociology

Psychology

None

25. What is true about Machine Learning?

a. Machine Learning (ML) is that field of computer science

b. ML is a type of artificial intelligence that extract patterns out of raw data by using an

algorithm or method.

c. The main focus of ML is to allow computer systems learn from experience without being

explicitly programmed or human intervention.

d. All of the above

26. Which of the following are ML methods?

a. based on human supervision

b. supervised Learning

c. semi-reinforcement Learning

d. All of the above

27. Direct Attached Storage is accessible in only a single machine?

a. True

b. False

28. Which plot is the most suitable for viewing the density in an area?

Heatmap

Countplot

Line plot

None of the above

29. Which is the most suitable plot for the analysis of run rate of two teams?

Line chart

Scatter plot

Count plot

Bar chart

30. for data preparation which of the following steps are required:

a. Sorting

b. Filtering the raw data

a. Only a

b. Only b

c. Both a and b

d. Neither a or b

31. Which of the following statements is correct for the supervised learning?

a. Supervised learning allows you to collect data or produce a data output from the previous

experience

b. Helps you to optimize performance criteria using experience

c. Supervised machine learning helps you to solve various types of real-world computation

problems

d. All of the above

32. Which of the following statements is correct for the unsupervised learning?

a. Unsupervised machine learning finds all kind of unknown patterns in data

b. Unsupervised methods help you to find features which can be useful for categorization.

c. It is taken place in real time, so all the input data to be analyzed and labeled in the

presence of learners

d. All of the above

33. Which type of Data Can be used for Regression??

Continuous

Discrete

Categorical

None of the above

34. Can classification be performed on both structured and unstructured data?

a. Yes

b. No

35. What is Clustering??

Grouping same features together

Categorizing the Object

Mining the Data

All of the above

36. Which of the recommender system type is based on the historical data?

Content-Based

Collaborative Filtering

Both

None

37. Who has coined the terms hyper text, hyper links?

Edgar F. Codd

James GoslingSir

Time Berners Lee

Denis Ritchie

38. Choose among the options which are the benefits of data storage?

Reliable data preservation

Data continuity and Flexibility

Effective security for protected files

All of the above

39. Choose among the options what are the different components for Data acquisition? a. Sensors

b. Signal Conditioning c. Analog-to-Digital Converter d. Computer with DAQ software

Only a

Both a and b

a, b and c

All of the above

40. Why association is important?

a. It tries to find some interesting relations or associations among the variables of

dataset

b. It groups the data with same features

c. None of the above

41. Physical storage of data:

1.CD-ROM

2.Distributed database

3.Cloud storage

4.None of the above

Solution- 1.CD-ROM

42. Importance of data:

1.It helps to analyze and visualize the performance

2.It helps to recommend correct options to the customers

3.It helps to solve complex problems

4.All the above

Solution- 4.All the above

ABES Engineering College, Ghaziabad

Department of Applied Science

Unit-3 (Multiple Choice Questions)

What are the two components of Natural Language Processing??’

Language Understanding and Language Generation

Reasoning and Expert

Knowledge and Computer Vision

None of the above

Which one is not a step in Natural Language Processing??

Lexical Analysis

Syntactic Analysis

Semantic Analyis

None of the above

Which one is not an Application of Natural Language Processing??

Speech Recognition

Machine Translation

Chatbots

None of the above

Which Python Library is to be used in implementing Language processing??

NLTK

SPACY

Gensim

Text blob

All of the above

None of the above

What are the different types of Speech Recognition??

Speaker Dependent

Speaker Independent

Speaker Adaptive

All of the above

Natural Language processing is used in-

Text classification

Topic modeling

Chatbots

All of the above

Which of the following is an application of NLP?

Summarizing a text or article

Predicting the genre of books

Speech recognition

All of the above

Sentiment analysis is an area of:

Computer vision

Natural language processing

Data analysis

Data mining

Spam Filtering is an example of which technique??

Linear Regression

Logistics Regression

Classification

Clustering

Association

10.

Which of the following is true about Topic Modelling?

It’s a natural language processing task

It is unsupervised learning

LDA(latent Dirichlet allocation) can be used

All of the above

11.

Convolutional Neural Network is used inImage classification

Text classification

Computer vision

All of the above

12.

Sentiment analysis is used todetect polarity of a text

detect the impact of a text

Both A and B

None

13.

Which of the following is a kind of text summarization?

Topic-based summarization

Extraction-based summarization

History-based summarization

All of the above

14.

Natural Language Processing is an field of

Computer Science

Linguistics

Artificial Intelligence

FOR IMPORTANT NOTES TOUCH TO "!! ADITYA !!"

STUDY ZONE

All of the above

15.

NLP is concerned with the interactions between computers and human (natural)

languages.

True

False

16.

Modern NLP algorithms are based on machine learning, especially statistical machine

learning.

True

False

17.

Choose form the following areas where NLP can be useful.

Automatic Text Summarization

Automatic Question-Answering Systems

Information Retrieval

All of the above

18.

Machine Translation

Converts one human language to another

Converts human language to machine language

Converts any human language to English

Converts Machine language to human language

19.

Morphological Segmentation

Discourse Analysis

Separate words into individual morphemes and identify the class of the morphemes

Is an extension of propositional logic

None of the above

20.

Who is the father of Natural Language Processing?

Enjamin Bandler

Richard Bandler

Elijah Bandler

Alan Turing

21.

Which among the following is not an application of natural language programming (nlp)?

Chat bot

Speech Recognition

Sentimental Analysis

Market Basket Analysis

22.

What are the two subfields of Natural language processing?

context and expectations

recognition and synthesis

semantics of pragmatics

generation and understanding

23.

What is natural language processing good for?

Summarize blocks of text

Identify the type of entity extracted

Automatically generate keyword tags

All of the Above

24.

One of the main challenge/s of NLP is.............

Handling Tokenization

Handling POS-Tagging

Handling Ambiguity of Sentences

All of the Above

25.

Which of the following is an application of NLP?

Alexa

Cortana

Google Assistant

None of the above

26.

Which of the below are NLP use cases?

Speech Biometric

Facial Recognition

Text Summarization

Detecting objects from an image

27.

Which of the following is an NLP task that involves determining all referring

expressions that point to the same real-world entity?

Coreference resolution

Named entity recognition

Information extraction

All of the above

28.

Which are the applications of speech recognition??

smartphones

voice dialing and voice search

speech-to-text processing

All of the above

29.

Speech Recognition is

It is the ability for a machine or program to identify words spoken aloud and convert

them into readable text

Speech recognition is the capability of an electronic device to understand spoken words

Speech recognition, also known as automatic speech recognition (ASR), computer speech

recognition, or speech-to-text, is a capability which enables a program to process human speech

into a written format.

All of the above

30.

Which is not the Step of NLP are :Lexical analysis

Syntactic analysis

Semantic analysis

Error analysis

31.

Which statement is correct ??

NLU is difficult than NLG

NLU is easy than NLG

NLU and NLG are equally difficult

There is no relation.

32.

How many Components of NLP are there?

33.

What are the input and output of an NLP system?

Speech and noise

Noise and Written Text

Noise and value

Speech and Written Text

34.

Which is not the advantage of chat bot?

Bots are a lot easier to install than mobile apps

Bots are not easily distributed Quality

mobile apps are expensive to build, maintain and deploy than chatbots.

24-hour availability

35.

Which is not the name of chatbot?

DoNotPay

Replika

self learning

BabyCentre

36.

Which is the approach of machine translation??

All of the above

rule based machine translation

statistical machine translation

neural machine translation

37.

Ans:

What is the Full form of NLU??

Natural Language Understanding

38.

Ans:

What is the Full form of NLG??

Natural Language Generation

14. The incorrect statement for a Convolutional Neural Network are:

a. The height and width of the filter in CNN must be less than the size of input

b. The Pooling layer progressively increases the spatial size of the representation

c. It uses both linear and non-linear activation functions

d. The last few layers are fully connected layers and computation on these layers are very

time consuming

Solution- 1.The height and width of the filter in CNN must be less than the size of input

Reason- This is because the height and width of the filter in CNN must not be less than the size

of input.

15. A Convolutional Neural Network is able to successfully capture the Spatial and Temporal

dependencies:

a. True

b. False

Solution- 1.True

Reason- Yes this true, because a ConvNet is able to successfully capture the Spatial and

Temporal dependencies in an image through the application of relevant filters.

16. Different types of normalization in Deep Neural Networks are

a. Output

b. Batch

c. Group

d. Instance

1.a,b,c

2.b,c,d

3.d,a,b

4.d,a,c

Solution- 2.b,c,d

Reason- Different types of normalization in Deep Neural Networks are batch, group, instance,

layer, weight etc..

17. Applications of CNNs are:

a. Recommender systems

b. AlexNet

c. Natural Language Processing

d. Pooling

FOR IMPORTANT NOTES TOUCH TO "!! ADITYA !!"

STUDY ZONE

1.a,b

2.b,d

3.a,c

4.a,d

Solution- 4.a,d

Reason- This is because recommender system is an application of CNN and Pooling layers are

used to reduce the dimensions of the feature maps in CNN.

18. Which of the following statements are correct for GAN?

a. GANs are useful for unsupervised learning, supervised learning, semi-supervised learning, and

reinforcement learning

b. Generative model technique learns to generate the data with the same statistics of training data

c. At each iteration the goal of generator is to minimize the classification error and the goal of

discriminator is to maximize the classification error.

d. The discriminator could tell the difference between images of a cat and a dog and generative

model could generate new images of animals that look like real animals.

1.a,b,c

2.a,b,d

3.a,c,d

4.b,c,d

Solution- 2.a,b,d

Reason- All the three a, b and d options are true.

19. A generative model:

a. Captures the joint probability p(X,Y)

b. Captures the conditional probability p(Y|X)

c. Includes the distribution of data itself

d. Cannot predict the next word in sequence

1.a,b

2.a,c

3.a,d

4.b,c

Solution- 2. a, c

Reason- A generative model includes the distribution of the data itself, and tells you how

likely a given example is. For example, models that predict the next word in a sequence are

typically generative models (usually much simpler than GANs) because they can assign a

probability to a sequence of words. and it. It also captures the joint probability p(X,Y)

20. The discriminative model:

a. Draw boundaries in the data space as it tells the difference between handwritten 0s and 1s.

b. Captures the joint probability p(X,Y)

c. Captures the conditional probability p(Y|X)

d. Learns to distinguish the generator’s fake data from real data

1.a,b,c

2.a,b,d

3.a,c,d

4.b,c,d

Solution- 3. a,c,d

Reason- The discriminative model tries to tell the difference between handwritten 0’s and

1’s by drawing a line in the data space. It captures the conditional probability p(Y|X) and

Learns to distinguish the generator’s fake data from real data

21. Choose the incorrect statements from the following

a. The discriminator uses the real data as negative examples during training

b. The discriminator uses the fake data as negative examples during training

c. The portion of the GAN that trains the generator model includes random input

d. None of the above

Solution- a.The discriminator uses the real data as negative examples during training

Reason- The generated instances become negative training examples for the

discriminator. The discriminator learns to distin

guish the generator’s fake data from real data.

22. Choose the correct statements from the following

a. Most universal approximation theorems can be parsed into two classes. The first quantifies the

approximation capabilities of neural networks with an arbitrary number of artificial neurons and

the second quantifies an arbitrary number of hidden layers

b. A neural network can represent any function provided it has sufficient capacity

c. Not all architectures can represent any function

d. None of the above

1.a,b,c

2.b,c,d

3.d,a,b

4.d,a,c

Solution- 1.a,b,c

Reason- All the above options a,b and c are true. As Most of the universal approximation

theorems can be parsed into two class. The first class quantifies the approximation capabilitiesof

neural networks with an arbitrary number of artificial neurons and the second quantifies an

arbitrary numberof hidden layers

23. Interesting applications of Generative Adversarial Networks (GANs) are:

a.Photo Inpainting

b.Culinary arts (as making a pizza)

c.Face aging

d.All the above

Solution- d. All the above

Reason- Photo Inpainting, Culinary arts (as making a pizza), Face aging all are the applications

of Generative Adversarial Networks (GANs)

24. Applications of Deep Learning are:

a.Self-driving cars

b.Fake news detection

c.Virtual Assistants

d.All the above

Solution- d. All the above

Reason- Self-driving cars, Fake news detection and virtual assistants all are the applications of

deep learning including healthcare, fraud detection etc..

25. The inputs for a single layer neural network are 1, 3, 2 and the weights of links connecting

input neurons to the output neuron are 2, 2, and 3 then the output will be (Identity activation

function is used in output neuron):

a.6

b.14

c.12

d.None of the above

Solution- b. 14

Reason- by using this formula – Output = w1 * x1 + w2 * x2 + w3 * x3

26. Which of the following is not a type of Artificial Neural Network?

a.Perceptron

b.Radial Basis Functions

c.Random Forest

d.Autoencoder

Solution- c. Random Forest

Reason- Both the Random Forest and Neural Networks are different techniques that learn

differently but can be used in similar domains. Random Forest is a technique of Machine

Learning while Neural Networks are exclusive to Deep Learning.

27. What is the limitation of deep learning?

a.Amount of data

b.Computational expensive

c.Data Labeling

d.All the above

Solution- d. All the above

Reason- Amount of data, computational expenses and data labelling all three are the limitation

of deep learning.

28. The number of nodes in the hidden layer is 8 and the output layer is 5. The maximum number

of connections from the hidden layer to the output layer are:

a.40

b.Less than 40

c.More than 40

d.It is an arbitrary value

Solution- a. 40

Reason- it is a fully connected direct graph, the number of connections are multiple of nodes in

hidden layer and output layer.

29. Recurrent Neural Networks (RNN) are used for

a.Businesses Help securities traders to generate analytic reports

b.Detecting fraudulent credit-card transaction

c.Providing a caption for images

d.All of the above

Solution- d. All of the above

Reason- All of the above options are true. This is because RNN is used to Help securities traders

to generate analytic reports, Detecting fraudulent credit-card transaction and to provide a caption

for images.

30. Types of RNN are:

a.LSTM

b.Boltzman machine

c.Hopfield network

d.a and b

Solution- 4. a and b

Reason- A Boltzmann machine (also called stochastic Hopfield network with hidden units or

Sherrington–Kirkpatrick model with external field or stochastic Ising-Lenz-Little model) is

a type of stochastic recurrent neural network. LSTM networks are a type of RNN that uses

special units in addition to standard units.

31. What is perceptron?

a.a single layer feed-forward neural network with pre-processing

b.an auto-associative neural network

c.a double layer auto-associative neural network

d.a neural network that contains feedb

Solution- a. a single layer feed-forward neural network with pre-processing

Reason- It is the simplest type of feedforward neural network , a feedforward neural

network with no hidden units. Thus, a perceptron has only an input layer and an output layer.

32. Bidirectional RNN:

a.Trained to predict both the positive and negative directions of time simultaneously.

b.Applications are speech recognition, handwritten recognition etc.

c.After forward and backward passes are done, the weights are updated

d.All the above

Solution- d. All the above

Reason- All the above options are true.

33. Which of the following is a subset of machine learning?

a. Numpy

b. SciPy

c. Deep Learning

d. All of the above

View Answer

Ans : c

34. Which of the following is/are Common uses of RNNs?

a. BusinessesHelp securities traders to generate analytic reports

b. Detect fraudulent credit-card transaction

c. Provide a caption for images

d. All of the above

Ans : d

35. The universal approximation theorem says that neural networks can approximate any

function.

a. TRUE

b.FALSE

36. It is important to realize that the word used is approximate, this means that the function

computed is not exact. However, this approximation can be improved as the number of

computation units i.e. neurons are increased in the layer and it can be fit to the desired accuracy.

a. TRUE

b.FALSE

37. Which of the following is true?

(i) On average, neural networks have higher computational rates than conventional computers.

(ii) Neural networks learn by example.

(iii) Neural networks mimic the way the human brain works.

a) All of the mentioned are true

b) (ii) and (iii) are true

c) (i), (ii) and (iii) are true

d) None of the mentioned

Answer: a

Explanation: Neural networks have higher computational rates than conventional computers

because a lot of the operation is done in parallel. That is not the case when the neural network is

simulated on a computer. The idea behind neural nets is based on the way the human brain

works. Neural nets cannot be programmed, they can only learn by examples.

38. Which of the following is true for neural networks?

(i) The training time depends on the size of the network.

(ii) Neural networks can be simulated on a conventional computer.

(iii) Artificial neurons are identical in operation to biological ones.

a) All of the mentioned

b) (ii) is true

c) (i) and (ii) are true

d) None of the mentioned

Answer: c

Explanation: The training time depends on the size of the network; the number of neuron is

greater and therefore the number of possible ‘states’ is increased. Neural networks can be

simulated on a conventional computer but the main advantage of neural networks – parallel

execution – is lost. Artificial neurons are not identical in operation to the biological ones.

39. What are the advantages of neural networks over conventional computers?

(i) They have the ability to learn by example

(ii) They are more fault tolerant

(iii)They are more suited for real time operation due to their high ‘computational’ rates

a) (i) and (ii) are true

b) (i) and (iii) are true

c) Only (i)

d) All of the mentioned

Answer: d

Explanation: Neural networks learn by example. They are more fault tolerant because they are

always able to respond and small changes in input do not normally cause a change in output.

Because of their parallel architecture, high computational rates are achieved.

40. Which is true for neural networks?

a) It has set of nodes and connections

b) Each node computes it’s weighted input

c) Node could be in excited state or non-excited state

d) All of the mentioned

Answer: d

Explanation: All mentioned are the characteristics of neural network.

41. Which answer explains better the Convolution?

a. Understand the model features and selecting the best.

b. Detect key features in images, respecting their spatial boundaries.

c.It is the first step to use CNN.

d. It is a technique to standardize the dataset.

42. What is the biggest advantage utilizing CNN?

a. Little dependence on pre processing, decreasing the needs of human effort developing its

functionalities.

b.It works well both for Supervised and Unsupervised Learning.

c. It is easy to understand and fast to implement.

d. It has the highest accuracy among all alghoritms that predicts images.

AI Unit-5 MCQ’s

Q:1. Choose the incorrect statement:

1.Speech recognition is a way of encoding and decoding analog signals

2.Differently abled people can use speech recognition system.

3.The first speech recognition systems were focused on numbers not words

4.None of the above

Q:2. Voice search engines are:

a. Google Assistant

b. Siri

c. Alexa

d. Cortana

1.a,b,c,d

2.b,c,d

2.d,a,b

2.d,a,c

Q:3. Types of speech recognition systems

1.Speaker independent

2.Speaker dependent

3.Speaker adaptive

4.All the above

Q:4. Steps of speech recognition system include

a. Analog to digital conversion

b. Wavelets and multiresolution processing

c. Use of acoustic and language model

d. Segmentation

1.a,b

2.b,c

3.c,a

4.a,d

Q:5. Applications of speech recognition systems are

a. Home automation

b. Voice dialing

c. Color processing

d. Translation

1.a,b,c

2.a,b,d

3.a,c,d

4.b,c,d

Solution- 2.a,b,d

Q:6. In computer vision

a. The tasks include methods for acquiring, processing, analyzing and

understanding digital images

b. Most computer vision systems rely on image sensors, which detect

electromagnetic radiation, which is typically in the form of either visible or infrared light

c. The working of visual cortex of a dog has introduced the concept of edge

detection.

d. All the above

1.a,b

2.b,c

3.c,d

4.a,d

Q:7. How computer vision works

a. Acquiring an image

b. Processing the image

c. Analyzing the image

d. Understanding the image

1.a,b,c,d

2.a,b,c

3.d,a,b

4.d,a,c

Q:8. Potential application areas of robots

a. Military robots

b. Drones

c. Medical robot

d. None of the above

1.a,b,c

2.b,c,d

3.a,b,d

4.d,a,c

Q:9. Artificial Intelligence techniques can

a. Analyze large amount of data

b. Take complicated decision easily

c. Replace humans in near future from almost all type of jobs

d. Be used in Logistic and Supply chain management

1.a,b,c

2.b,c,d

3.a,b,d

4.d,a,c

Q:10. How a robot works?

1.Uses pre-programmed instructions stored in CPU

2.It need special hardware with sensors and effectors

3.Robot sensors send feedback to controllers

4.All the above

Q:11. Applications of face recognition system are

a. Security system

b. Attendance system

c. Smartphone’s unlocking system

d. Video surveillance system

1.a,b,c,d

2.a,b,c

3.b,c,d

4.d,a,b

Q:12. Image recognition steps are

a. Extract pixel features from an image

b. Prepare labeled images for training data

c. Train the model to be able to categorize images

d. None of the above

1.a,b,c

2.b,c,d

2.d,a,b

2.d,a,c

Q:13. Applications of image recognition system are

a. Driverless car technology

b. Document clustering

c. Gaming

d. All the above

1.a,b

2.b,c

3.a,c

4.c,d

Q:14. Object detection

a. It is a computer vision technique that allows us to identify and locate objects in

an image or video

b. Object detection allows us to at once classify the types of things found while

also locating instances of them within the image

c. Draws a box around each object whereas image recognition assigns a label to an

image

d. It has a capability which enables a program to process human speech into a

written format

1.a,b,c

2.b,d,a

3.a,c,d

4.b,c,d

Q:15. Applications of object detection are

a. Video surveillance

b. Crowd counting

c. Spam/Non-spam classification

d. Self-driving cars

1.a,b,c

2.a,b,d

3.a,c,d

4.b,c,d

Q:16. Methods for object detection are

1.Viola–Jones method

2.Deep Learning approaches

3.Both (a) and (b)

4.None of the above

Q:17. In which step of the processing, assigning a label (e.g., “dog”) to an object

based on its descriptors is done?

1.Object recognition

2.Morphological processing

3.Segmentation

4.Representation

Q:18. What is the first and foremost step in Image Processing?

1.Morphological processing

2. Compression

3.Image acquisition

4.Image enhancement

Q:19. Image recognition tools are:

a. Clarifai

b. IBM Watson Visual Recognition

c. Amazon Lex

d. Scikit-image

1.a,b,c

2.b,c,d

3.a,b,d

4.d,a,c

Q:20. Choose an incorrect statement

1.Image detection involves predicting the class of one object in an image.

2.Object localization refers to identifying the location of one or more objects

in an image and drawing abounding box around their extent

3.Object detection combines these two tasks and localizes and classifies one or

more objects in an image

4.Detection is the process of identification and classification is the categorization

of the object based on a previously defined classes or types.

Q:21. At what points, a continuous image is digitized?

Sampling

Vertex

Contour

Random

Q:22. How many stages are there to identify the person’s face?

One

Two

Three

Four

Reason : Capture , extraction, comparison, match/no match

Q:23. What are the advantages of face recognition?

Easy to use

Inexpensive biometric

Expensive biometric

Both a and b

Q:24. _________ are the applications of face recognition for commercial use

Residential security

Voter verification

Banking using ATM

All of the above

Q:25. _________ are the applications of face recognition for government use

Law enforcement

Security/counter-terrorism

Immigration

All of the above

Q:26. The applications of the face recognition are __________

Criminal identification

Surveillance

Tracking attendance

All of the above

Q:27. The face recognition is a biometric tool?

True

False

Q:28. Who introduced the first semi-automated system for face recognition?

H.C.Wolf

C.BISSON

W.BLEDSOE

All of the above

Q:29. Which one is not a physiological type biometric?

Voice scan

Finger scan

Iris scan

All of the above

Q:30. Computer vision is divided into _________ basic categories

A. 1

B. 2

C. 3

D. 4

Q:31. The input and output of image processing are?

A. signal and image

B. signal only

C. image only

D. depends on input

Q:32. Which of the following is an Applications of Computer Vision?

A. Robotics

B. Medicine

C. Security

D. All of the above

Q:33. What is pixel?

a) Pixel is the elements of a digital image

b) Pixel is the elements of an analog image

c) Pixel is the cluster of a digital image

d) Pixel is the cluster of an analog image

Q:34. What is the expanded form of JPEG?

a) Joint Photographic Expansion Group

b) Joint Photographic Experts Group

c) Joint Photographs Expansion Group

d) Joint Photographic Expanded Group

Q:35. A computer program with AI can not answer the generic questions it is

meant to solve.

A. TRUE

B. FALSE

C. AI is not used to answer question

D. None of the Above

Q:36. Which of the following is an application of AI?

A. Gaming

B. Expert Systems

C. Vision Systems

D. All of the above

Q:37. What enables people to recognize people, animals and inanimate objects

reliably?

a) Speech

b) Vision

c) Hear

d) Perception

Q:38. Which are recognized by vision?

a) Objects

b) Activities

c) Motion

d) Both Objects & Activities

Q:39. The characteristics of computer system capable of thinking, reasoning and

learning is known as:

a) Machine intelligence

b) Human Intelligence

c) Artificial Intelligence

d) All of the above

Artificial Intelligence for Engineers (KMC201) Question Bank

Unit-1 An Overview to AI

Unit- 1

1.1

1.2

1.3

1.4

1.5

Topics

The evolution of AI to the present

Various approaches to AI

What should all engineers know about AI?

Other emerging technologies

AI and ethical concerns

SET-1

1. LISP was created by?

a) John McCarthy

b) Marvin Minsky

c) Alan Turing

d) Allen Newell and Herbert Simon

Answer: a

2. A.M. turing developed a technique for determining whether a computer could or could not demonstrate the

artificial Intelligence, Presently, this technique is called __________

a) Turing Test

b) Algorithm

c) Boolean Algebra

d) Logarithm

Answer: a

3. DARPA, the agency that has funded a great deal of American Artificial Intelligence research, is part of the

Department of __________

a) Defense

b) Energy

c) Education

d) Justice

Answer: a

4. Which of these schools was not among the early leaders in Artificial Intelligence research?

a) Dartmouth University

b) Harvard University

c) Massachusetts Institute of Technology

d) Stanford University

Answer: b

5. A certain Professor at the Stanford University coined the word ‘artificial intelligence’ in 1956 at a conference

held at Dartmouth College. Can you name the Professor?

a) David Levy

b) John McCarthy

c) Joseph Weizenbaum

d) Hans Berliner

Answer: b

6. Who is the “father” of artificial intelligence?

a) Fisher Ada

b) John McCarthy

c) Allen Newell

d) Alan Turning

Answer: b

7. The conference that launched the AI revolution in 1956 was held at?

a) Dartmouth

b) Harvard

c) New York

d) Stanford

Answer: a

8. One method of programming a computer to exhibit human intelligence is called modeling or __________

a) simulation

b) cognitization

c) duplication

d) psychic amelioration

Answer: a

9. The performance of an agent can be improved by __________

a) Learning

b) Observing

c) Perceiving

d) None of the mentioned

Answer: a

10. A completely automated chess engine (Learn from previous games) is based on?

a) Strong Artificial Intelligence approach

b) Weak Artificial Intelligence approach

c) Cognitive Artificial Intelligence approach

d) Applied Artificial Intelligence approach

Answer: a

Explanation: Strong Artificial Intelligence aims to build machines that can truly reason and solve problems. These

machines must be self-aware and their overall intellectual ability needs to be indistinguishable from that of a human

being. Strong Artificial Intelligence maintains that suitably programmed machines are capable of cognitive mental states.

11. A basic line following robot is based on __________

a) Strong Artificial Intelligence approach

b) Weak Artificial Intelligence approach

c) Cognitive Artificial Intelligence approach

d) Applied Artificial Intelligence approach

Answer: b

Explanation: Weak Artificial Intelligence deals with the creation of some form of computer-based artificial intelligence

that cannot truly reason and solve problems, but can act as if it were intelligent. Weak Artificial Intelligence holds that

suitably programmed machines can simulate human cognition.

12. Which of the following task/tasks Artificial Intelligence could not do yet?

a) Understand natural language robustly

b) Web mining

c) Construction of plans in real time dynamic systems

d) All of the mentioned

Answer: d

Explanation: These are the areas in which need more focus for improvements.

13. What among the following is/are the example of the intelligent agent/agents?

a) Human

b) Robot

c) Autonomous Spacecraft

d) All of the mentioned

Answer: d

Explanation: Humans can be looked upon as agents. They have eyes, ears, skin, taste buds, etc. for sensors; and hands,

fingers, legs, mouth for effectors. Robots are agents. Robots may have camera, sonar, infrared, bumper, etc. for sensors.

They can have grippers, wheels, lights, speakers, etc. for actuators. Autonomous Spacecraft takes decision on its own

based on perceptions.

14. Which of the following could be the approaches to Artificial Intelligence?

a) Strong Artificial Intelligence

b) Weak Artificial Intelligence

c) Applied Artificial Intelligence

d) All of the mentioned

Answer: d

Explanation: Strong Artificial Intelligence aims to build machines that can truly reason and solve problems.

Weak Artificial Intelligence deals with the creation of some form of computer-based artificial intelligence that cannot

truly reason and solve problems, but can act as if it were intelligent.

Applied Artificial Intelligence aims to produce commercially viable “smart” systems.

In the Cognitive Artificial Intelligence approach, a computer is used to test theories about how the human mind works.

15. External actions of the agent is selected by __________

a) Perceive

b) Performance

c) Learning

d) Actuator

Answer: b

Explanation: It depends on how you want to improve and what the performance measures are.

16. What was originally called the “imitation game” by its creator?

a) The Turing Test

b) LISP

c) The Logic Theorist

d) Cybernetics

Answer: a

17. Which particular generation of computers is associated with artificial intelligence?

a) Second

b) Fourth

c) Fifth

d) Third

Answer: c

18. What of the following is considered a pivotal event in the history of Artificial Intelligence?

a) 1949, Donald O, The organization of Behavior

b) 1950, Computing Machinery and Intelligence

c) 1956, Dartmouth University Conference Organized by John McCarthy

d) 1961, Computer and Computer Sense

Answer: c

19. What is the field that investigates the mechanics of human intelligence?

a) history

b) cognitive science

c) psychology

d) sociology

Answer: b

20. What is the name of the computer program that simulates the thought processes of human beings?

a) Human logic

b) Expert reason

c) Expert system

d) Personal information

Answer: c

21. What is the name of the computer program that contains the distilled knowledge of an expert?

a) Database management system

b) Management information System

c) Expert system

d) Artificial intelligence

Answer: c

22. A computer program that contains expertise in a particular domain is called?

a) intelligent planner

b) automatic processor

c) expert system

d) operational symbolizer

Answer: c

23. What is the primary interactive method of communication used by humans?

a) reading

b) writing

c) speaking

d) all of the mentioned

Answer: c

24. Which is the first AI programming language?

a) BASIC

b) FORTRAN

c) IPL(Inductive logic programming)

d) LISP

Answer: d

25. Which is not the commonly used programming language for AI?

a) PROLOG

b) Java

c) LISP

d) Perl

Answer: d

Explanation: Because Perl is used as a script language, and not of much use for AI practice. All others are used to

generate an artificial program.

26. What is an ‘agent’?

a) Perceives its environment through sensors and acting upon that environment through actuators

b) Takes input from the surroundings and uses its intelligence and performs the desired operations

c) A embedded program controlling line following robot

d) All of the mentioned

Answer: d

Explanation: An agent is anything that can be viewed as perceiving and acting upon the environment through the sensors

and actuators. Mean it takes input from its environment through sensors, performs operation and gives output through

actuators.

27. Which of the following is an advantage of using an expert system development tool?

a) imposed structure

b) knowledge engineering assistance

c) rapid prototyping

d) all of the mentioned

Answer: d

28. An AI system developed by Daniel Bobrow to read and solve algebra word problems.

a)SHRDLU

b) SIMD

c) BACON

d) STUDENT

Answer: d

29. In which year John McCarthy coined the term Artificial Intelligence?

A. 1950

B. 1956

C. 1953

D. 1959

Answer: b

30. Computational intelligence is a form of_____

A. Knowledge management

B. Singularity

C. Artificial intelligence

D. case-based reasoning

Answer: c

Artificial Intelligence for Engineers (KMC201) Question Bank

Unit-2 Data & Algorithms

Unit- 2

2.1

2.2

2.3

2.4

2.5

Topics

History Of Data

Data Storage And Importance of Data and its Acquisition

The Stages of data processing

Data Visualization

Regression, Prediction & Classification

SET-1

1. Which modifies the performance element so that it makes better decision?

a) Performance element

b) Changing element

c) Learning element

d) None of the mentioned

Answer: c

Explanation: A learning element modifies the performance element so that it can make better decision.

2. What is used in determining the nature of the learning problem?

a) Environment

b) Feedback

c) Problem

d) All of the mentioned

Answer: b

Explanation: The type of feedback is used in determining the nature of the learning problem that the agent faces.

3. What takes input as an object described by a set of attributes?

a) Tree

b) Graph

c) Decision graph

d) Decision tree

Answer: d

Explanation: Decision tree takes input as an object described by a set of attributes and returns a decision.

4. How the decision tree reaches its decision?

a) Single test

b) Two test

c) Sequence of test

d) No test

Answer: c

Explanation: A decision tree reaches its decision by performing a sequence of tests.

5. Which of the following is the model used for learning?

FOR

IMPORTANT

NOTES TOUCH TO "!! ADITYA

Decision

trees

b) Neural networks

c) Propositional and FOL rules

d) All of the mentioned

Answer: d

Explanation: Decision trees, Neural networks, Propositional rules and FOL rules all are the models of learning.

6. Automated vehicle is an example of ______

a) Supervised learning

b) Unsupervised learning

c) Active learning

d) Reinforcement learning

Answer: a

Explanation: In automatic vehicle set of vision inputs and corresponding actions are available to learner hence it’s an

example of supervised learning.

7. In which of the following learning the teacher returns reward and punishment to learner?

a) Active learning

b) Reinforcement learning

c) Supervised learning

d) Unsupervised learning

Answer: b

Explanation: Reinforcement learning is the type of learning in which teacher returns reward or punishment to learner.

8. Decision trees are appropriate for the problems where ___________

a) Attributes are both numeric and nominal

b) Target function takes on a discrete number of values.

c) Data may have errors

d) All of the mentioned

Answer: d

Explanation: Decision trees can be used in all the conditions stated.

9. Which of the following is not an application of learning?

a) Data mining

b) WWW

c) Speech recognition

d) None of the mentioned

Answer: d

Explanation: All mentioned options are applications of learning.

10. In an Unsupervised learning ____________

a) Specific output values are given

b) Specific output values are not given

c) No specific Inputs are given

d) Both inputs and outputs are given

Answer: b

Explanation: The problem of unsupervised learning involves learning patterns in the input when no specific output values

are supplied. We cannot expect the specific output to test your result. Here the agent does not know what to do, as he is

not aware of the fact what propose system will come out. We can say an ambiguous un-proposed situation.

11. A _________ is a decision support tool that uses a tree-like graph or model of decisions and their possible

consequences, including chance event outcomes, resource costs, and utility.

a) Decision tree

b) Graphs

c) Trees

d) Neural Networks

Answer: a

Explanation: Refer the definition of Decision tree.

12. What is Decision Tree?

a) Flow-Chart

b) Structure in which internal node represents test on an attribute, each branch represents outcome of test and each leaf

node represents class label

c) Flow-Chart & Structure in which internal node represents test on an attribute, each branch represents outcome of test

and each leaf node represents class label

d) None of the mentioned

Answer: c

Explanation: Refer the definition of Decision tree.

13. Choose from the following that are Decision Tree nodes?

a) Decision Nodes

b) End Nodes

c) Chance Nodes

d) All of the mentioned

Answer: d

14. Decision Nodes are represented by ____________

a) Disks

b) Squares

c) Circles

d) Triangles

Answer: b

15. Chance Nodes are represented by __________

a) Disks

b) Squares

c) Circles

d) Triangles

Answer: c

16. End Nodes are represented by __________

a) Disks

b) Squares

c) Circles

FOR

IMPORTANT NOTES TOUCH TO

Triangles

Answer: d

17. Which of the following are the advantage/s of Decision Trees?

a) Possible Scenarios can be added

b) Use a white box model, If given result is provided by a model

c) Worst, best and expected values can be determined for different scenarios

d) All of the mentioned

Answer: d

Artificial Intelligence for Engineers (KMC201) Question Bank

Unit-3 Natural Language Processing

Unit- 3

3.1

3.2

3.3

3.4

3.5

Topics

Speech recognition

Natural language understanding

Natural language generation

Chatbots

Machine Translation

SET-1

1. A natural language generation program must decide __________

a) what to say

b) when to say something

c) why it is being used

d) both what to say & when to say something

Answer: a

2. The Face Recognition system is based on?

a) Strong Artificial Intelligence approach

b) Weak Artificial Intelligence approach

c) Cognitive Artificial Intelligence approach

d) Applied Artificial Intelligence approach

Answer: d

Explanation: Applied Artificial Intelligence approach aims to produce commercially viable “smart” systems such as, for

example, a security system that is able to recognize the faces of people who permitted to enter a particular building.

Applied Artificial Intelligence has already enjoyed considerable success.

3. When talking to a speech recognition program, the program divides each second of your speech into 100

separate __________

a) Codes

b) Phonemes

c) Samples

d) Words

Answer: c

4. Ambiguity may be caused by ______________

a) syntactic ambiguity

b) multiple word meanings

c) unclear antecedents

d) all of the mentioned

Answer: d

5. What are the two subfields of Natural language processing?

a) symbolic and numeric

b) time and motion

c) algorithmic and heuristic

d) understanding and generation

Answer: d

6. People overcome natural language problems by _____________

a) grouping attributes into frames

b) understanding ideas in context

c) identifying with familiar situations

d) both understanding ideas in context & identifying with familiar situations

Answer: d

7. Natural language understanding is used in _____________

a) natural language interfaces

b) natural language front ends

c) text understanding systems

d) all of the mentioned

Answer: d

8. What enables people to recognize people, animals and inanimate objects reliably?

a) Speech

b) Vision

c) Hear

d) Perception

Answer: b

Explanation: Vision enables people to recognize people, animals and inanimate objects reliably. It is customary to use

object recognition.

9. How many types of recognition are there in artificial intelligence?

a) 1

b) 2

c) 3

d) 4

Answer: c

Explanation: The three types of recognition are biometric identification, content-based image retrieval and handwriting

recognition.

10. Which are recognized by vision?

a) Objects

b) Activities

c) Motion

d) Both Objects & Activities

Answer: d

Explanation: Vision is used to recognize not only objects, but also activities.

11. Which provides a framework for studying object recognition?

a) Learning

b) Unsupervised learning

c) Supervised learning

d) None of the mentioned

Answer: c

Explanation: Supervised learning or pattern classification provides a framework for studying object recognition.

12. Which is the only way to learn about the different kinds of human faces?

a) Perception

b) Speech

c) Learning

d) Hearing

Answer: c

13. Where does the Hidden Markov Model is used?

a) Speech recognition

b) Understanding of real world

c) Both Speech recognition & Understanding of real world

d) None of the mentioned

Answer: a

14. What is the dominant modality for communication between humans?

a) Hear

b) Speech

c) Smell

d) None of the mentioned

Answer: b

Explanation: Speech is the dominant modality for communication between humans and reliable speech recognition

between machines.

15. What kind of signal is used in speech recognition?

a) Electromagnetic signal

b) Electric signal

c) Acoustic signal

d) Radar

Answer: c

Explanation: Acoustic signal is used to identify a sequence of words uttered by a speaker.

16. What is viewed as problem of probabilistic inference?

a) Speech recognition

b) Speaking

c) Hearing

d) Utterance

Answer: a

Explanation: Speech recognition is viewed as problem of probabilistic inference because different words can sound the

FOR IMPORTANT NOTES TOUCH TO "!! ADITYA !!"

same.

17. Which model gives the probability of each word following each other word?

a) Bigram model

b) Diagram model

c) Gram model

d) Speech model

Answer: a

Explanation: Bigram model gives the probability of each word following each other word in speech recognition.

18. What is the study of how the language sounds?

a) Speechology

b) Biology

c) Trilogy

d) Phonology

Answer: d

19. What are periodic changes in pressure that propagate through the air?

a) Air waves

b) Sound waves

c) Rate

d) None of the mentioned

Answer: b

Explanation: Sound waves are periodic changes in pressure that propagate through the air and it can be measured by a

microphone.

20. What is called as the properties of the signal that extend over interval?

a) Hops

b) Rate

c) Frames

d) All of the mentioned

Answer: c

Explanation: Speech system summarize the properties of the signal that extend over interval called frames.

21. What is the field of Natural Language Processing (NLP)?

a) Computer Science

b) Artificial Intelligence

c) Linguistics

d) All of the mentioned

Answer: d

22. What is the main challenge/s of NLP?

a) Handling Ambiguity of Sentences

b) Handling Tokenization

c) Handling POS-Tagging

d) All of the mentioned

Answer: a

Explanation: There are enormous ambiguity exists when processing natural language.

23. Choose form the following areas where NLP can be useful.

a) Automatic Text Summarization

b) Automatic Question-Answering Systems

c) Information Retrieval

d) All of the mentioned

Answer: d

24. Which of the following includes major tasks of NLP?

a) Automatic Summarization

b) Discourse Analysis

c) Machine Translation

d) All of the mentioned

Answer: d

25. What is Machine Translation?

a) Converts one human language to another

b) Converts human language to machine language

c) Converts any human language to English

d) Converts Machine language to human language

Answer: a

Explanation: The best known example of machine translation is google translator.

26. Many words have more than one meaning; we have to select the meaning which makes the most sense in

context. This can be resolved by ____________

a) Fuzzy Logic

b) Word Sense Disambiguation

c) Shallow Semantic Analysis

d) All of the mentioned

Answer: b

Explanation: Shallow Semantic Analysis doesn’t cover word sense disambiguation.

27. Given a sound clip of a person or people speaking, determine the textual representation of the speech.

a) Text-to-speech

b) Speech-to-text

c) All of the mentioned

d) None of the mentioned

Answer: b

Explanation: NLP is required to linguistic analysis.

Artificial Intelligence for Engineers (KMC201) Question Bank

Unit-4 Artificial Neural Networks

Unit- 4

4.1

4.2

4.3

4.4

4.5

Topics

Deep Learning

Recurrent Neural Networks

Convolutional Neural Networks

The Universal Approximation Theorem

Generative Adversarial Networks

SET-1

1. An Artificial Neural Network Is based on?

a) Strong Artificial Intelligence approach

b) Weak Artificial Intelligence approach

c) Cognitive Artificial Intelligence approach

d) Applied Artificial Intelligence approach

Answer: c

Explanation: In the Cognitive Artificial Intelligence approach, a computer is used to test theories about how the human

mind works, for example, theories about how we recognize faces and other objects, or about how we solve abstract

problems.

2. What among the following is/are the example of the intelligent agent/agents?

a) Human

b) Robot

c) Autonomous Spacecraft

d) All of the mentioned

Answer: d

3. External actions of the agent is selected by __________

a) Perceive

b) Performance

c) Learning

d) Actuator

Answer: b

Explanation: It depends on how you want to improve and what the performance measures are.

4. What is used in determining the nature of the learning problem?

a) Environment

b) Feedback

c) Problem

d) All of the mentioned

Answer: b

Explanation: The type of feedback is used in determining the nature of the learning problem that the agent faces.

5. What is perceptron?

a) a single layer feed-forward neural network with pre-processing

b) an auto-associative neural network

c) a double layer auto-associative neural network

d) a neural network that contains feedback

Answer: a

Explanation: The perceptron is a single layer feed-forward neural network. It is not an auto-associative network because

it has no feedback and is not a multiple layer neural network because the pre-processing stage is not made of neurons.

6. What are the advantages of neural networks over conventional computers?

(i) They have the ability to learn by example

(ii) They are more fault tolerant

(iii)They are more suited for real time operation due to their high ‘computational’ rates

a) (i) and (ii) are true

b) (i) and (iii) are true

c) Only (i)

d) All of the mentioned

Answer: d

Explanation: Neural networks learn by example. They are more fault tolerant because they are always able to respond

and small changes in input do not normally cause a change in output. Because of their parallel architecture, high

computational rates are achieved.

7. Which is true for neural networks?

a) It has set of nodes and connections

b) Each node computes it’s weighted input

c) Node could be in excited state or non-excited state

d) All of the mentioned

Answer: d

Explanation: All mentioned are the characteristics of neural network.

8. Which of the following is an application of NN (Neural Network)?

a) Sales forecasting

b) Data validation

c) Risk management

d) All of the mentioned

Answer: d

Explanation: All mentioned options are applications of Neural Network.

9. How to increase the brightness of the pixel?

a) Sound

b) Amount of light

c) Surface

d) Waves

Answer: b

Explanation: The brightness of a pixel in the image is proportional to the amount of light directed towards the camera.

10. Which of the following is true?

Single layer associative neural networks do not have the ability to:

(i) perform pattern recognition

(ii) find the parity of a picture

(iii)determine whether two or more shapes in a picture are connected or not

A. (ii) and (iii) are true

B. (ii) is true

C. All of the mentioned

D. None of the mentioned

ANSWER: A

11. Which is true for neural networks?

A. it has set of nodes and connections

B. Each node computes it’s weighted input

C. Node could be in excited state or non-excited state

D. All of the mentioned

ANSWER: D

12. What is back propagation?

A. It is another name given to the curvy function in the perceptron

B. It is the transmission of error back through the network to adjust the inputs

C. It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn

D. None of the mentioned

ANSWER: C

13. Why are linearly separable problems of interest of neural network researchers?

A. Because they are the only class of problem that network can solve successfully

B. Because they are the only class of problem that Perceptron can solve successfully

C. Because they are the only mathematical functions that are continue

D. Because they are the only mathematical functions you can draw

ANSWER: B

14. Which of the following is not the promise of artificial neural network?

A. It can explain result

B. It can survive the failure of some nodes

C. It has inherent parallelism

D. It can handle noise

ANSWER: A

15. Neural Networks are complex with many parameters.

A. Linear Functions

B. Nonlinear Functions

C. Discrete Functions

D. Exponential Functions

ANSWER:

Artificial Intelligence for Engineers (KMC201) Question Bank

Unit-5 Applications

Unit- 5

5.1

5.2

5.3

5.4

5.5

Topics

Image and face recognition

Object recognition

Speech Recognition besides Computer Vision

Robots

Applications

SET-1

1. Artificial Intelligence has its expansion in the following application.

a) Planning and Scheduling

b) Game Playing

c) Diagnosis

d) All of the mentioned

Answer: d

Explanation: All sectors require intelligence and automation for its working.

2. What is an ‘agent’?

a) Perceives its environment through sensors and acting upon that environment through actuators

b) Takes input from the surroundings and uses its intelligence and performs the desired operations

c) A embedded program controlling line following robot

d) All of the mentioned

Answer: d

Explanation: An agent is anything that can be viewed as perceiving and acting upon the environment through the sensors

and actuators. Mean it takes input from its environment through sensors, performs operation and gives output through

actuators.

3. What enables people to recognize people, animals and inanimate objects reliably?

a) Speech

b) Vision

c) Hear

d) Perception

Answer: b

Explanation: Vision enables people to recognize people, animals and inanimate objects reliably. It is customary to use

object recognition.

4. Which are recognized by vision?

a) Objects

b) Activities

c) Motion

d) Both Objects & Activities

Answer: d

Explanation: Vision is used to recognize not only objects, but also activities.

5. Which provides a framework for studying object recognition?

a) Learning

b) Unsupervised learning

c) Supervised learning

d) None of the mentioned

Answer: c

Explanation: Supervised learning or pattern classification provides a framework for studying object recognition.

6. Which is the only way to learn about the different kinds of human faces?

a) Perception

b) Speech

c) Learning

d) Hearing

Answer: c

7. Automated vehicle is an example of ______

a) Supervised learning

b) Unsupervised learning

c) Active learning

d) Reinforcement learning

Answer: a

Explanation: In automatic vehicle set of vision inputs and corresponding actions are available to learner hence it’s an

example of supervised learning.

8. Which of the following is not an application of learning?

a) Data mining

b) WWW

c) Speech recognition

d) None of the mentioned

Answer: d

Explanation: All mentioned options are applications of learning

9. Which of the following terms refers to the rotational motion of a robot arm?

a) swivel

b) axle

c) retrograde

d) roll

Answer: d

10. Which of the following terms IS NOT one of the five basic parts of a robot?

a) peripheral tools

b) end effectors

c) controller

d) drive

Answer: a

11. The number of moveable joints in the base, the arm, and the end effectors of the robot determines_________

a) degrees of freedom

b) payload capacity

c) operational limits

d) flexibility

Answer: a

12. For a robot unit to be considered a functional industrial robot, typically, how many degrees of freedom would

the robot have?

a) three

b) four

c) six

d) eight

Answer: c

13. Decision support programs are designed to help managers make __________

a) budget projections

b) visual presentations

c) business decisions

d) vacation schedules

Answer: c

14. Which of the following is not an application of AI?

a) Intelligent Robots

b) Handwriting Recognition

c) Speech Recognition

d) Content mining

Answer : d

Ticker

Artificial intelligence All MCQ's -(Part-3)

Post a Comment

0 Comments

Most Popular