001.

Which of the following methods DOES NOT prevent a model from overfitting to the B
training set?
A Dropout B Pooling
C Early Stopping D Data Augmentation
002. RNNs stands for? A
A Recurrent Neural Networks B Report Neural Networks
C Receives Neural Networks D Recording Neural Networks
003. Which neural networks has only one hidden layer between the input and output NO
AN
SW
ER
GIV
EN
A Shallowneural networks B Deepneural networks
C Feedfarward Neural Networks D RecurrentNeural Networks
004. Deep learning algorithms are________ more accurate than machine learning D
algorithms in image classification.
A 33% B 0.37%
C 0.4% D 0.41%
005. How many layers Deep learning algorithms are constructed?. B
A 2 B 3
C 4 D 5
006. Which of the following is a subset of machine learning? C
A SciPy B Numpy
C Deep Learning D Machine Learning
007. When did deep learning start? A
A 1943 B 1962
C 1978 D 1989
008. Who is father of deep learning? D
A Ilya Sutskever B David Rumelhart
C Alex Krizhevsky D Frank Rosenblatt
009. Supervised learning and unsupervised clustering both require at least one A
A Hiddenattribute B Outputattribute
C Inputattribute D Categoricalattribute
010. Another name for an output attribute B
A Predictivevariable B Independentvariable
C Estimatedvariable D Dependentvariable
011. Supervised learning differs from unsupervised clustering in that supervised learning B
requires
A Atleast one input attribute B Inputattributes to be categorical
C Atleast one output attribute D outputattributes to be categorical
012. The input image has been converted into a matrix of size 28 X 28 and a kernel/filter of C
size 7 X 7 with a stride of 1. What will be the size of the convoluted matrix?
A 20x20 B 21x21
C 22x22 D 25x25
013. In which of the following applications can we use deep learning to solve the problem D
A Proteinstructure prediction B Predictionof chemical reactions
C Detectionof exotic particles D Allof the above
014. Computers are best at learning A
A Facts B Concepts
C Procedure D principles
015. Which of the following is well suited for perceptual tasks C
A Feedfarward Neural Networks B RecurrentNeural Networks
C Convolutionalneural networks D Reinforcementlearning
016. Which of the following techniques perform similar operations as a dropout in a neural A
network
A Bagging B Boosting
C Stacking D Pooling
017. A__________ begins by hypothesizing a sentence (the symbol S) and successively C
predicting lower level constituents until individual preterminal symbols are written.
A bottow-up parser B top parser
C top-down parser D bottom parser
018. Choose from the following that are decision tree nodes A
A Decisionnodes B Treenodes
C Networksnodes D Parentnodes
019. Decision nodes are represented by__________ B
A Disk B Square
C Circle D Triangle
020. Chance nodes are represented by__________ C
A Disk B Square
C Circle D Triangle
021. A ____ is a decision support tool that uses a tree-like graph or model of decisions and A
their possible consequences , including chance event outcomes, resource cost and
utility
A Decisiontree B Graphs
C Neuralnetworks D Trees
022. The action _______ of a robot arm specify to Place block A on block B. A
A STACK(A,B) B LIST(A,B)
C QUEUE(A,B) D ARRAY(A,B)
023. The number of nodes in the input layer is 10 and the hidden layer is 5. The maximum A
number of connections from the input layer to the hidden layer are
A 50 B less than 50
C more than 50 D It is an arbitrary value
024. Which of the following statements is true when you use 11 convolutions in a CNN? D
A It cannot help in dimensionality B It cannot be used for feature pooling
reduction
C It can not suffers less over fitting due D It suffers less over fitting due to small
to small kernel size kernel size
025. For a neural network, which one of these structural assumptions is the one that most A
affects the trade-off between under fitting (i.e. a high bias model) and over fitting (i.e. a
high variance model):
A The number of hidden nodes B The learning rate
C The initial choice of weights D The use of a constant-term unit input
026. Given two Boolean random variables, A and B, where P(A) = , P(B) = 1/3, and P(A | B) D
= , what is P(A | B)?
A 1/6 B 1/4
C 3/4 D 1
027. Which of the following guidelines is applicable to initialization of the weight vector in a B
fully connected neural network.
A Shouldnot set it to zero since B Shouldnot set it to zero since
otherwise it will cause overfitting otherwise (stochasti gradient descent
willexplore a very small space
C Shouldset it to zero since otherwise it D
causes a bias Should set it to zero in
order to preserve symmetry across all
neurons
028. Kernel Methods also called ? B
A Method B Functions
 C Algorithms D Machine
029. In Model based learning methods, an iterative process takes place on the ML models C
that are built based on various model parameters, called ?
A mini-batches B optimizedparameters
C hyperparameters D superparameters
030. ___________ refers to a model that can neither model the training data nor generalize C
to new data.
A good fitting B over fitting
C under fitting D Bad fitting
031. End nodes are represented by__________ D
A Disk B Square
C Circle D Triangle
032. A model of language consists of the categories which does not include ________. B
A System Unit B structural units.
C data units D empirical units
033. Confusion matrix is a metric for. B
A Clustering B Classification
C Regression D analysis
034. train_test_split() method splits the dataset into. A
A 2 parts B 3 parts
C 4 parts D 5 Parts
035. Empty fields in a dataset can be determined using. B
A df.isempty() B df.isna()
C df.ismissing() D df.missing()
036. The goal of _______________ is to find the optimal separating hyperplane that C
maximizes the margin of the training data.
A Stochastic6 Gradient Descent. B Nave Bayes
C Support Vector Machine D Decision Trees
037. which one of following is not a data clearning process. A
A mean absolute error B handling stop words
C missing values management D mean square error
038. Machine learning is usually classified into categories. B
A 2 B 3
C 4 D 5
039. The SVM uses what is called a? B
A Data Transformed B Kernal Trick
C Optimal Boundry D Polynomial Kernel
040. Logistic Regression algorithm uses. C
A support vector B data point distance
C sigmoid function D exponential function
041. Encounter Some Missing Values, Corrupted Data, And Remove Unnecessary Data B
Called?
A Data Mining B Data Cleaning
C Redundancy Control D Data Where Housing
042. Robots Arm Is Called? A
A Actuator B Effector
C Manipulator D Sensors
043. The Conference That Launches The Ai Revolution Was Held In? B
A Harvard B Dartmouth
C New York D London
044. Normalize Words Into Its Base Form Or Root Form? B
A Spanning B Stemming
C Sorting D Normalization
045. Formula Of A* Algorithm Is. A
 A F(N)=G(N) + H(N) B F(N)=G(N) H(N)
C F(N)=G(N) / H(N) D F(N)=G(N) * H(N)
046. 8- Puzzle Problem Without Heuristic Vales Are Also Called? A
A Uninformed Search B Informed Search
C Bubble Sort D Binary Search
047. cross_val_score technique divides the dataset into. C
A 5 parts B 10 parts
C 15 parts D user defined
048. BOW is a(n) D
A algorithm B function
C attribute D feature extrating technique
049. Which lens is faster, a lens with an f-number of 1.4 or 2.0 or 2.4 or 4.2? A
A F-numberof 1.4 B F-numberof 2.0
C F-numberof 2.4 D F-numberof 4.2
050. What is the trend in software nowadays? A
A tobring computer more & more closer B tosolve complex problems
to user
C tobe task specific D tobe versatile
051. Whats the main point of difference between human & machine intelligence? A
A human perceive everything as a B human have emotions
pattern while machine perceive it
merely as data
C human have more IQ & intellect D human have sense organs
052. Example of a unsupervised feature map? B
A textrecognition B voicerecognition
C imagerecognition D patternrecognition
053. Which is the correct way to get the maximum depth of field? A
A Fullyclose the lens aperture. B Fullyopen the lens aperture.
C Partiallyclose the lens aperture D Partiallyopen the lens aperture
054. What is the FOV (field of view) in the Y direction of a macro lens with a 3x-optical A
magnification attached to a camera with a CCD size of 3.6 (0.14") mm in the Y
direction?
A 1.2mm (0.047") B 10.8mm (0.43")
C 0.2mm(0.0047) D 1.08mm(0.43)
055. To Overcome The Limitation Of Stemming Is Used ? A
A Lemmatization B Normalization
C Erosion D Spanning
056. On Which Platform Alexa Assistant Is Working ? B
A Pixabay B Amazon
C Google D Yahoo
057. The CPN provides practical approach for implementing? C
A patterapproximation B patternclassification
C patternmapping D patternclustering
058. What is the feature that doesnt belongs to pattern classification in feeddorward neural B
networks?
A recallis direct B deltarule learning
C nonlinear processing units D twolayers
059. What is the feature that doesnt belongs to pattern mapping in feeddorward neural D
networks?
A recallis direct B deltarule learning
C nonlinear processing units D twolayers
060. What is Artificial Intelligence? C
A ArtificialIntelligence is a field that aims B ArtificialIntelligence is a field that aims
to make humans more intelligent to improve the security
 C ArtificialIntelligence is a field that aims D ArtificialIntelligence is a field that aims
to develop intelligent machines to mine the data
061. Drawbacks of template matching are? B
A timeconsuming B highlyrestricted
C moregeneralized D lessrestricted
062. What is the use of MLFFNN? D
A torealize structure of MLP B tosolve pattern classification problem
C tosolve pattern mapping problem D torealize an approximation to a MLP
063. What is plasticity in neural networks? A
A inputpattern keeps on changing B inputpattern has become static
C outputpattern keeps on changing D outputis static
064. What is stability plasticity dilemma ? C
A system can neither be stable nor B static inputs & categorization cant be
plastic handled
C dynamic inputs & categorization cant D dynamic inputs & categorization can
be handled be handled
065. Based on which of the following parameter Artificial Intelligence is categorized? C
A Basedon functionally only B Basedon capabilities only
C Basedon capabilities and functionally D Itis not categorized
066. Which of the following is a component of Artificial Intelligence? A
A Learning B Training
C Designing D Puzzling
067. What is the function of an Artificial Intelligence Agent? C
A Mappingof goal sequence to an B Workwithout the direct interference of
action the people
C Mappingof precept sequence to an D Mappingof environment sequence to
action an action
068. Which of the following is not a type of Artificial Intelligence agent? D
A LearningAI agent B Goal-basedAI agent
C Simplereflex AI agent D Unity-basedAI agent
069. Which of the following is an application of Artificial Intelligence? B
A Ithelps to exploit vulnerabilities to B Languageunderstanding and
secure the firm problem-solving (Text analytics and
NLP)
C Easyto create a website D Ithelps to deploy applications on the
cloud
070. In how many categories process of Artificial Intelligence is categorized? C
A categorizedinto 5 categories B processesare categorized based on
the input provided
C categorizedinto 3 categories D processis not categorized
071. Which of the following is the branch of Artificial Intelligence? A
A MachineLearning B Cyberforensics
C Full-StackDeveloper D NetworkDesign
072. What is the goal of Artificial Intelligence? C
A Tosolve artificial problems B Toextract scientific causes
C Toexplain various sorts of intelligence D Tosolve real-world problems
073. Which of the following machine requires input from the humans but can interpret the D
outputs themselves?
A Actuators B Sensor
C Agents D AIsystem
074. ________ number of informed search method are there in Artificial Intelligence. A
A 4 B 3
C 2 D 1
075. The total number of proposition symbols in AI are _______ B
 A 3 B 2
C 1 D 0
076. The total number of logical symbols in AI are ______ B
A Thereare 3 logical symbols B Thereare 5 logical symbols
C Numberof logical symbols are based D Logicalsymbols are not used
on the input
077. What is the function of the system Student? C
A programthat can read algebra word B systemwhich can solve algebra word
problems only problems but not read
C systemwhich can read and solve D systemwhich can not read and solve
algebra word problems algebra word problems
078. Which of the following is not an application of artificial intelligence? D
A Face recognition system B Chatbots
C LIDAR D DBMS
079. Which of the following is not the commonly used programming language for Artificial A
Intelligence?
A Perl B Java
C PROLOG D LISP
080. What is the name of the Artificial Intelligence system developed by Daniel Bobrow? B
A programknown as BACON B systemknown as STUDENT
C programknown as SHRDLU D systemknown as SIMD
081. What is the total number of quantification available in artificial intelligence? D
A 4 B 3
C 1 D 2
082. Deep web is also known as ______________ D
A Freenet B Darknet
C ARPANET D Hiddenweb
083. Which of the following produces hypotheses that are easy to read for humans? B
A MachineLearning B ILP
C First-orderlogic D Propositionallogic
084. Face Recognition system is based on which type of approach? B
A WeakAI approa B AppliedAI approach
C CognitiveAI approach D StrongAI approach
085. On which of the following approach A basic line following robot is based? B
A Appliedapproach B Weakapproach
C Strongapproach D Cognitiveapproach
086. Which of the following environment is strategic? B
A Rational B Deterministic
C Partial D Stochastic
087. What is the name of Artificial Intelligence which allows machines to handle vague D
information with a deftness that mimics human intuition?
A Humanintelligence B Booleanlogic
C Functionallogic D Fuzzylogic
088. The two key ideas of deep learning for computer vision________ B
A SupportVector Machines and loss B Convolutionalneural networks and
function backpropagation
C Deepneural networks and kernel D Deepneural networks and loss
functions function
089. In which neural net architecture, does weight sharing occur? D
A RecurrentNeural Network B Convolutionalneural Network
C FullyConnected Neural Network D Recurrentand convolutional neural
networks
090. What is shallow learning in deep learning? B
A Machinelearning tend to focus on B Machinelearning tend to focus on
 learning 512 layers of representations learning only one or two layers
of thedata ofrepresentations of the data
C Machinelearning tend to focus on D Machinelearning tend to focus on
learning 64 layers of representations learning 10 layers of representations
of thedata of thedata
091. The popular computer scientist _____________ has coined the term deep web in the C
year 2001.
A Mr.Tim Lee B Mr.Narcos Maralli
C Mr.Michael K. Bergman D Mr.Ken Thompson
092. The popular computer scientist Mr. Michael K. Bergman has coined the term deep web B
in the year ____________
A 2000 B 2001
C 2002 D 2003
093. The __________ was a huge marketplace of Dark Web specifically famous for selling A
of illegal drugs & narcotics as well as you can find a wide range of other goods for sale.
A SilkRoad B CottonRoad
C DarkRoad D DrugRoad
094. What is loss function in deep learning? A
A Tocontrol the output of a neural B Tocalculate loss in banks
network, you need to be able to
measurehow far this output is from
what you expected
C Theseare the predicted values only D Theseare true targets of data
095. Which of the following would have a constant input in each epoch of training a Deep A
Learning model?
A Weightbetween input and hidden B Weightbetween hidden and output
layer layer
C Biasesof all hidden layer neurons D Activationfunction of output layer
096. You are part of a data science team that is working for a national fast-food chain. You B
create a simple report that shows trend: Customers who visit the store more often and
buy smaller meals spend more than customers who visit less frequently and buy larger
meals. What is the most likely diagram that your team created?
A multiclassclassification diagram B linearregression and scatter plots
C pivottable D K-meanscluster diagram
097. The number of nodes in the input layer is 10 and the hidden layer is 5. The maximum D
number of connections from the input layer to the hidden layer are_______
A morethan 50 B lessthan 50
C itis an arbitrary value D 50
098. Which statement is true? B
A Deeplearning is an analogue B Deeplearning is a mathematical
framework for learning framework for learning
representations from data representations fromdata
C Deeplearning is a biological D Deeplearning is a digital framework
framework for learning for learning representations from data
representations frombrain
099. SVM stands for_______ C
A SupportVector Mechanism B SuperVisual Machine
C SupportVector Machine D SupportVector Model
100. The input image has been converted into a matrix of size 2828 and a kernel/filter of A
size 77 with a stride of 1. What will be the size of the convoluted matrix?
A 22x22 B 2121
C 2020 D 2525
101. Assume a simple MLP model with 3 neurons and inputs=1,2,3. The weights of the D
input neurons are 4,5, and 6 respectively. Assume the activation function is a linear
 constant value of 3. What will be the output?
A 64 B 128
C 32 D 96
102. Which of the following is not the promise of artificial neural network? A
A it can explain result B it can survive the failure of some
nodes
C it has inherent parallelism D it can handle noise
103. The network that involves backward links from output to the input and hidden layers is C
called as ____.
A selforganizing maps B perceptrons
C recurrentneural network D multilayered perceptron
104. Why are linearly separable problems of interest of neural network researchers? B
A because they are the only class of B because they are the only class of
problem that network can solve problem that perceptron can solve
successfully successfully
C because they are the only D because they are the only
mathematical functions that are mathematical functions you can draw
continue
105. A 3-input neuron is trained to output a zero when the input is 110 and a one when the C
input is 111. After generalization, the output will be zero when and only when the input
is:
A 110 or 011 or 101 B 010 or 100 or 110 or 101
C 000 or 010 or 110 or 100 D 100 or 111 or 101 or 001
106. What is back propagation? C
A it is another name given to the curvy B it is the transmission of error back
function in the perceptron through the network to adjust the
inputs
C it is the transmission of error back D it is the transmission of push back
through the network to allow weights through the network to adjust the
to be adjusted so that the network inputs
can learn.
107. Why is the XOR problem exceptionally interesting to neural network researchers? D
A becauseit can be expressed in a way B becauseit is complex binary operation
that allows you to use a neural that cannot be solved using
network neuralnetworks
C becauseit can be solved by a single D becauseit is the simplest linearly
layer perceptron inseparable problem that exit
108. Following is also called as exploratory learning: C
A supervised learning B active learning
C unsupervised learning D reinforcement learning
109. What will take place as the agent observes its interactions with the world? A
A learning B hearing
C perceiving D speech
110. In which of the following learning the teacher returns reward and punishment to B
learner?
A active learning B reinforcement learning
C supervised learning D unsupervised learning
111. Different learning method does not include: D
A memorization B analogy
C deduction D introduction
112. Following are the advantage/s of Decision Trees. Choose that apply. D
A possible scenarios can be added B for data including categorical
variables with different number of
levels, information gain in decision
 trees are biased in favor of those
attributes with more levels
C worst, best and expected values can D use a white box model, if given result
be determined for different scenarios is provided by a model
113. Which of the following is the model used for learning? D
A decision trees B neural networks
C propositional and fol rules D Support vector machine
114. Automated vehicle is an example of ______. A
A supervised learning B unsupervised learning
C active learning D reinforcement learning
115. Factors which affect the performance of learner system does not include D
A representation scheme used B training scenario
C type of feedback D good data structures
116. The process by which you become aware of messages through your sense is called D
A organization B sensation
C interpretation-evaluation D perception
117. What takes input as an object described by a set of attributes? D
A tree B graph
C decision graph D decision tree
118. How many things are concerned in design of a learning element? C
A 1 B 2
C 3 D 4
119. How many types are available in machine learning? C
A 1 B 2
C 3 D 4
120. Which is used for utility functions in game playing algorithm? D
A linear polynomial B weighted polynomial
C polynomial D linear weighted polynomial
121. What takes input as an object described bya set of attributes? D
A tree B graph
C decision graph D decision tree
122. Which of the following strategies would NOT be effective at improving your A
communication competence?
A recognize the people, objects, and B recognize that each persons frame of
situations remain stable over time perception is unique
C be active in perceiving D distinguish facts from inference
123. A perception check is D
A a cognitive bias that makes us listen B a method teachers use to reward
only to information we already agree good listeners in the classroom.
with.
C any factor that gets in the way of D a response that allows you to state
good listening and decreases our your interpretation and ask your
ability to interpret correctly. partner whether or not that
interpretation is correct.
124. Selective retention occurs when A
A we process, store, and retrieve B we make choices to experience
information that we have already particular stimuli
selected, organized, and interpreted
C we make choices to avoid particular D we focus on specific stimuli while
stimuli ignoring other stimuli
125. Susan is so beautiful; I bet she is smart too. This is an example of A
A the halo effect B the primary effect
C a self-fulfilling prophecy D the recency effect
126. ____ prevents you from seeing an individual as an individual rather than as a member C
 of a group.
A cultural mores B stereotypes
C schematas D attributions
127. When you get fired from your job and you determine it is because your boss dislikes D
you, you are most likely exhibiting
A self-promotion B fundamental attribution error
C over-attribution D self-serving bias
128. Mindless processing is C
A careful, critical thinking B inaccurate and faulty processing
C information processing that relies D processing that focuses on unusual or
heavily on familiar schemata novel events
129. Which closely resembles propositional definite clause? D
A resolution B inference
C conjuction D first-order definite clauses
130. Which are more suitable normal form to be used with definite clause? C
A positive literal B negative literal
C generalized modus ponens D neutral literal
131. How many types of image processing techniques are there in image perception? C
A 1 B 2
C 3 D 4
132. Which provides agents with information about the world they inhabit? B
A sense B perception
C reading D hearing
133. How to increase the brightness of the pixel? B
A sound B amount of light
C surface D waves
134. How many kinds of reflection are available in image perception? B
A 1 B 2
C 3 D 4
135. What is meant by predicting the value of a state variable from the past? D
A specular reflection B diffuse reflection
C gaussian filter D smoothing
136. How many formal languages are used for stating propositions? B
A 1 B 2
C 3 D 4
137. How many proposition symbols are there in artificial intelligence? B
A 1 B 2
C 3 D 4
138. Where does the degree of belief are applied? A
A propositions B literals
C variables D statements
139. Which is mainly used for automated reasoning? C
A backward chaining B forward chaining
C logic programming D parallel programming
140. How can be the goal is thought of in backward chaining algorithm? D
A queue B list
C vector D stack
141. What form of negation does the prolog allows? A
A negation as failure B proposition
C substitution D negation as success
142. How many issues are available in describing degree of belief? B
A 1 B 2
C 3 D 4
143. Which technique is being investigated as an approach to automatic programming? B
 A generative cai B specification by example
C hierarchical planning D non-hierarchical planning
144. One definition of AI focuses on problem-solving methods that process: B
A smell B symbols
C touch D algorithms
145. Computers normally solve problem by breaking them down into a series of yes-or-no B
decisions represented by 1s and 0s. What is the name of the logic that allows
computers to assign numerical values that fail somewhere between 0 and 1?
A human logic B fuzzy logic
C boolean logic D operational logic
146. Which is a refutation complete inference procedure for propositional logic? C
A clauses B variables
C propositional resolution D proposition
147. What kind of clauses is available in Conjunctive Normal Form? A
A disjunction of literals B disjunction of variables
C conjunction of literals D conjunction of variables
148. Which sentence will be unsatisfiable if the CNF (Conjunction Normal Form) sentence is D
unsatisfiable?
A search statement B reading statement
C replaced statement D original statement
149. What is meant by factoring? B
A removal of redundant variable B removal of redundant literal
C addition of redundant literal D addition of redundant variable