Self Assessments

1. What is called as transposition table?

a. None of these
b. Hash table of previously seen positions
c. Next value in the search
d. Hash table of next seen positions
2. In language understanding, the levels of knowledge that does not include?
a. Syntactic b. Phonological c. Empirical d. Logical
3. The most significant phase in a genetic algorithm is
a. Crossover b. Selection c. Fitness function d. Mutation
4. What is perceptron?
a. a single layer feed-forward neural network with pre-processing
b. an auto-associative neural network
c. a neural network that contains feedback
d. a double layer auto-associative neural network
5. Neural Networks are complex functions with many parameter
a. Discreate b. Exponential c. Linear d. Non linear
6. Which of the following sentences are correct in reference to Information gain?
a. All of these
b. ID3 makes use of information gain
c. It is biased towards multi-valued attributes
d. The approach used by ID3 is greedy
7. Inference algorithm is complete only if
a. it can derive any sentence that is an entailed version & It is truth
preserving
b. It can derive any sentence
c. It can derive any sentence that is an entailed version
d. It is truth preserving
8. Charles Babbage and Boole who demonstrate the power of _______
a. Logic b. Computation logic c. Cognition logic d. all options true
9. In k-NN it is very likely to over fit due to the curse of dimensionality. Which of the
following option would you consider to handle such problem? 1). Dimensionality
Reduction 2). Feature selection
a. None of these b. 2 c. 1 and 2 d. 1
10. Which of the following is not type of learning?
a. Semi-unsupervised Learning c. Unsupervised Learning
b. Reinforcement Learning d. Supervised Learning
11. Who is a father of AI?
a. John McCarthy b. Nicklaus Wirth c. Seymour Papert d. Alain Colmerauer
12. Which of the following is a subset of population?
a. Sample b. Distribution c. Set d. Data
13. Learning symbolic representations of concepts known as:
a. Both a & b c. Artificial Intelligence
b. Machine Learning d. None of these
14. The autonomous acquisition of knowledge through the use of computer programs
is called
a. All of these c. Machine Learning
b. Deep learning d. Artificial Intelligence
15. Methods used for the calibration in Supervised Learning
 a. Isotonic Regression b. All of these c. Platt Calibration d. None of
these
16. Strong Artificial Intelligence is
a. a set of computer programs that produce output that would be considered
b. the embodiment of human intellectual capabilities within a computer
c. to reflect intelligence if it were generated by humans
d. the study of mental faculties through the use of mental models
implemented on a computer
17. What is the correct representation of GA?
a. GA(Fitness, Fitness_threshold) c. GA(Fitness,
Fitness_threshold, p, r )
b. GA(Fitness, Fitness_threshold, p, r, m) d. GA(Fitness,
Fitness_threshold, p)
18. evolution over many generations was directly influenced by the
experiences of individual organisms during their lifetime
a. Lamarckian b. Bayes c. None of these d. Baldwin
19. How many terms are required for building a Bayes model? A. 3

20. What is the approach of basic algorithm for decision tree induction?
a. Procedural b. Step by Step c. Greedy d. Top Down
21. Bayesian networks allow compact specification of:-
a. Belief c. Joint probability distributions
c. all true d. Propositional logic statements
22. The benefit of Naïve Bayes:-
a. It can be used for Binary as well as Multi-class
b. It is the most popular choice for text classification problems.
c. All of these
d. Naïve Bayes is one of the fast and easy ML algorithms to predict a class of
23. Which of these are types of crossover
a. Uniform b. Two point c. Single point d. All of these
24. ______ is used for AI because it supports the implementation of software that
computes with symbols very well.
a. ELIZA b. LISP c. NLP d. PROLOG
25. The Version space is:
a. All of these
b. The version space consists of only specific
c. None of these
d. The subset of all hypotheses is called the version space with respect
to the hypothesis space H and the training examples D, because it
contains all plausible versions of the target
26. The worldwide researchers are now focusing on developing machines with ___ AI.
a. None of these b. All General AI c. All Narrow AI d. All Super AI
27. The first AI programming language was called:
a. IPL b. FORTRAN c. LISP d. BASIC
28.Computer programs that mimic the way the human brain processes information
is called as
a. Deep Learning c. Machine Learning
b. Neural Networks d. None of these
29. Another name for an output attribute.
a. predictive variable c. dependent variable
 b. independent variable d. estimated variable
30. Which of the following is correct about the Naive Bayes?
a. All of these
b. Assumes that all the features in a dataset are independent
c. Assumes that all the features in a dataset are equally important
d. Both
31. An auto-associative network is
a. A single layer feed-forward neural network with pre-processing
b. A neural network that contains no loops
c. A neural network that has only one loop
d. A neural network that contains feedback
32. Which AI system not store memories or past experiences for future actions.
a. All Theory of mind c. All Reactive machine
b. None of these d. All Limited memory
33. What is true regarding back propagation rule?
a. There is no feedback of signal at nay stage
b. All of these
c. Error in output is propagated backwards only to determine weight updates
d. It is also called generalized delta rule
34. The hypothesis h1 is more-general-than hypothesis h2 ( h1 > h2) if and only if
h1≥h2 is true and h2≥h1 is false. We also say h2 is more-specific-than h1
a. The statement is true c. The statement is false
b. We cannot d. None of these
35. How many states are available in state-space search? a. 4
36. _____ AI is able to perform dedicated task.
a. Neural AI b. Narrow AI c. None of these d. General AI

37. Knowledge and reasoning also play a crucial role in dealing with environment.
a. Partially Observable
b. Completely Observable
c. Neither Completely nor Partially Observable
d. Only Completely and Partially Observable
38. The crossover operator produces two new offspring from
a. Two parent strings, by copying selected bits from one parent
b. Two parent strings, by copying selected bits from each parent
c. One parent strings, by copying selected bits from selected parent
38. What is Artificial intelligence?
a. Making a Machine intelligent
b. Putting more memory into Computer
c. Programming with your own intelligence
d. Putting your intelligence into Computer
39. A perceptron adds up all the weighted inputs it receives, and if it exceeds a
certain value, it outputs a 1, otherwise it just outputs a O. b. TRUE
40. In genetic algorithm process of selecting parents which mate and recombine to
create off-springs for the next generation is known as:
a. Tournament selection b. Parent selection c. Fitness sharing d. Rank
selection
41. Artificial Intelligence has its expansion in the following application.
a. Robotics b. Planning and Scheduling
 c. Game Playing
d. Planning and Scheduling,Game Playing andRobotics
42. A constructive approach in which no commitment is made unless it is necessary
to do so is
a. Opportunistic planning
b. Most commitment approach
c. Least commitment approach
d. Nonlinear planning
43. Visual clues that are helpful in computer vision include
a. height and weight
b. color and motion
c. color and motion, depth and texture
d. depth and texture
44. Supervised learning differs from unsupervised clustering in that supervised
learning requires
a. at least one input attribute.
b. output attributes to be categorical.
c. input attributes to be categorical.
d. at least one output attribute.
45. What is used to mitigate over fitting in a test set?
a. Validation dataset b. Over fitting set c. Evaluation set d. Training set
48. Which is identical to the closed list in Graph search?
a. Transposition table c. None of these
b. Depth-first search d. Hill climbing search algorithm
49. ILP stand for
a. Inductive Logic Program
b. Inductive Logical Program
c. Inductive Logic Programming
d. Inductive Logical programming
49. Decision Nodes are represented by which of the following
a. Squares b. Solar street light c. Triangles d. Circles
50. Which of the following is false regarding EM Algorithm?
a. The alignment provides an estimate of the base or amino acid composition of
each column in the site
b. The row-by-column composition of the site already available is used to
estimate the probability
c. None of these
d. The column-by-column composition of the site already available is used to
estimate the probability of finding the site at any position in each of the
sequences
51. The adjusted multiple coefficient of determination accounts for
a. the number of dependent variables in the model
b. unusually large predictors
c. the number of independent variables in the model
d. None of these
52. How many ways are available to solve the state-space search? ---- a. 2
53. FIND-S Algorithm starts from the most specific hypothesis and generalize it by
considering only
a. Negative or Positive b. Positive c. Negative d. None of these
54. The network that involves backward links from output to the input and hidden
layers is known as
a. Perceptrons c. Self organizing maps
b. Single layered perceptron d. Recurrent neural network
55. In Machine learning the module that must solve the given performance task is
known as:
a. Performance system b. Critic c. Generalizer d. All of
these
56. Genetic algorithm is a
a. None of these
b. Both A & B
c. Search technique used in computing to find true or approximate
solution to optimization and search problem
d. Sorting technique used in computing to find true or approximate solution to
optimization and sort problem
57. Which of the following is a widely used and effective machine learning algorithm
based on the idea of bagging?
a. Regression b. Random Forest c. Decision Tree d. Classification
58. What is/are true about Distance-weighted KNN?
a. None of these c. The distance of the neighbour is considered
b. Both A & B d. The weight of the neighbour is considered
59. ______ is a branch of computer science which deals with helping machines finds
solutions to complex problems in
a. Artificial Intelligence b. Internet of Things c. Cyber Security d. Embedded System
60. Which of the following classifications would best suit the student performance
classification systems?
a. If-.then-analysis c. Market-basket analysis
b. Cluster analysis d. Regression analysis
61. Which of the following is a disadvantage of decision trees?
a. None of these
b. Factor analysis
c. Decision trees are robust to outliers
d. Decision trees are prone to be over fit
62. The conference that launched the AI revolution in 1956 was held at:
a. Harvard b. Stanford c. Dartmouth d. New York
63. What is Machine Learning (ML)?
a. The selective acquisition of knowledge through the use of computer programs
b. The autonomous acquisition of knowledge through the use of computer
programs
c. The autonomous acquisition of knowledge through the use of manual programs
d. The selective acquisition of knowledge through the use of manual programs
64. A Hybrid Bayesian network contains
a. Only Discontinuous variable
b. Only Discrete variables
c. Both Discrete and Discontinuous variable
d. Both discrete and continuous variables
65. Treatment chosen by doctor for a patient for a disease is based on
a. Current symptoms plus some knowledge from the textbooks plus
experience
b. Current symptoms plus some knowledge from the textbooks
c. All of these
 d. Only current symptoms
66.Which of these schools was not among the early leaders in AI research?
a. Harvard University
b. Stanford University
c. Dartmouth University
d. Massachusetts Institute of Technology
67. How well a model is going to generalize in new environment is known as
a. Data Quality b. Transparent c. Implementation
68.What is the problem space of means-end analysis?
a. One initial state and one goal state
b. An initial state and one or more goal states
c. One or more initial states and one goal state
d. One or more initial states and one or more goal state
69. The process of forming general concept definitions from examples of concepts to
be learned.
a. induction b. Deduction c. abduction d. conjunction
70. What is the mathematical likelihood that something will occur?
a. None of these c. Naïve Bayes Classifier
b. Probability d. Classification
71. The Candidate-Elimination Algorithm represents the .
a. Solution Space b. Version Space c. All of these d. Elimination Space
72. Mathematically characterize the evolution over time of the population within a
GA based on the concept of
a. Crossover b. Don't care c. Schema d. Fitness function
73. Bayes’ theorem states that the relationship between the probability of the
hypothesis before getting the evidence P(H) and the probability of the hypothesis
after getting the evidence P(H∣E) is
a. all false c. [P(E) P(H) ] / P(E∣H)
b. [P(E∣H) P(E) ] / P(H) d. [P(E∣H)P(H)] / P(E)
74. Naïve Bayes algorithm is based on and used for solving classification problems.
a. Candidate elimination algorithm c. None of these
b. Bayes Theorem d. EM algorithm
75. General games involves
a. Multi-agent c. Neither Single-agent nor Multi-agent
b. Single-agent d. Only Single-agent and Multi-agent
76. What area of CLT tells “How many examples we need to find a good
hypothesis ?”?
a. Sample Complexity c. Computational Complexity
b. None of these d. Mistake Bound
77. Consider the following: (a) Evolution (b) Selection (c) Reproduction (d) Mutation
Which of the following are found in genetic algorithms?
a. a, b, c b. a, b c. All of these d. b, d
78. Which of the following is true for neural networks? 0) 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 these
79. ELIZA created by _____
a. Steve Russell c. Joseph Weizenbaum
 b. Alain Colmerauer d. John McCarthy
80. Bayes rule can be used for:-
a. Decreasing complexity c. Increasing complexity
b. Solving queries d. Answering probabilistic query
81. There are also other operators, more linguistic in nature, called that can be applied
to fuzzy set theory.
a. Hedgesb. Lingual Variable c. Fuzz Variable

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

a. Use a white box model, If given result is provided by a model
b. Worst, best and expected values can be determined for different scenarios
c. Possible Scenarios can be added
d. All of these
83. 65. Probability provides a way of summarizing the that comes from our
laziness and
a. Belief b. Randomness c. Uncertaintity d. Joint probability distributions
84. What is meant by consistent in state-space search?
a. Change in the desired literals c. No change in goal state
b. Not any change in the literals d. None of these
85. The most common issue when using ML is
a. Poor Data Quality b. Inadequate Infrastructure c. Lack of skilled
resources
86. Which of the following is the consequence between a node and its predecessors
while creating Bayesian network?
a. Functionally dependent
b. Dependent
c. Both Conditionally dependant & Dependant
d. Conditionally independent
87. When you find noise in data which of the following option would you consider in
k- NN
a. Noise can not be dependent on value of k
b. I will decrease the value of k
c. None of these
d. I will increase the value of k
88. Radial basis functions is closely related to distance-weighted regression, but it is
a. eager learning b. None of these c. concept learning d. lazy learning
89. GA techniques are inspired by
a. Anatomy b. Cytology c. Evolutionary d. Ecology
90. A multiple regression model has
a. more than one dependent variable
b. None of these
c. more than one independent variable
d. only one independent variable
91. _____ do not guarantee optimal/any solutions
a. Analytical b. Heuristic c. Value based d. Critical
92. In which of the following scenario a gain ratio is preferred over Information Gain?
a. When a categorical variable has very small number of category
b. When a categorical variable has very large number of category
c. Number of categories is the not the reason
93. Which of the following is a common use of unsupervised clustering?
 a. determine if meaningful relationships can be found in a dataset
b. evaluate the likely performance of a supervised learner model
c. detect outliers
d. determine a best set of input attributes for supervised learning
94. A 3-input neuron is trained to output a zero when the input is 110 and a one
when the input is 111. After generalization, the output will be zero when and only
when the input is?
a. 100 or 111 or 101 or 001 c. 000 or 010 or 110 or 100
b. 010 or 100 or 110 or 101 d. 000 or 110 or 011 or 101
95. Apple siri is a good example of ______ AI.
a. General AI b. Neural AI d. Narrow AI c. all false
96. A way to ensemble multiple classifications or regression
a. Boosting b. Stacking c. Bagging d. Blending
97. IBM’s deep blue system is example of ___.
a. None of these c. All Theory of mind
b. All Limited memory d. All Reactive machine
98. The idea behind _________AI to make such a system which could be smarter and
think like a human by its own.
a. Narrow AI c. Super AI d. General AI b. None of these
99. Targetted marketing, Recommended Systems, and Customer Segmentation are
applications in which of the following
a. Supervised Learning: Classification
b. Reinforcement Learning
c. Unsupervised Learning: Regression
d. Unsupervised Learning: Clustering
100. What is the meaning of generalized in statement “back propagation is a
generalized delta rule” ?
a. It has no significance
b. Because delta rule can be extended to hidden layer units
c. Because delta is applied to only input and output layers, thus making it more
simple and generalized
d. None of these
101.Ground literal is a literal that
a. does not contains any functions c. Contains only functions Answer
b. does not contains any variablesd. Contains only variables
102. Computational complexity of classes of learning problems depends on which of the
following?
a. The size or complexity of the hypothesis space considered by learner
b. All of these
c. The accuracy to which the target concept must be approximated
d. The probability that the learner will output a successful hypothesis
103. For the analysis of ML algorithms, we need
a. None of these c. Both A & B
b. Statistical learning theory d. Computational learning theory
104. Wumpus World is a classic problem, best example of
a. Single player Game
b. Reasoning with Knowledge
c. Knowledge based Game
d. Two player Game
105. What of the following is true regarding back propagation rule?
 a. It is a feedback neural network
b. Hidden layers output is not all important, they are only meant for supporting
input and output layers
c. None of these
d. Actual output is determined by computing the outputs of units for
each hidden layer
106.What does the Bayesian network provides?
a. Complete description of the problem
b. None of these
c. Partial description of the domain
d. Complete description of the domain
107. Feature of ANN in which ANN creates its own organization or representation of
information it receives during learning time is
a. Supervised Learning c. What-If Analysis
b. Self Organization d. Adaptive Learning
108. Zero sum game has to be a game.
a. Three player b. Multiplayer c. Two player d. Single player
109. What is/are the problem solving methods for RL?
a. Temporal-difference learning c. Dynamic programming
b. All of these d. Monte Carlo Methods
110. Classification problems are distinguished from estimation problems in that
a. classification problems require the output attribute to be numeric.
b. classification problems are designed to predict future outcome.
c. classification problems do not allow an output attribute.
d. classification problems require the output attribute to be categorical.
111. For a multiple regression model, SST = 200 and SSE = 50 The multiple coefficient
of determination is
a. 4 b. None of these c. 0.75 d. 0.25

112. Which of the following will be true about k in K-Nearest Neighbor in terms of Bias?
a. Can't say b. When you increase the k the bias will be increased
c. None of these d. When you decrease the k the bias will be increases
113. provides way and means of weighing up the desirability of goals and the
likelihood of achieving
a. Utility theory c. Decision theory
b. Probability theory d. Bayesian networks
114. ________are algorithms that learn from their more complex environments (hence
eco) to generalize, approximate and simplify solution logic.
a. Fuzzy Set b. Ecorithms c. Fuzzy Relational DB d. None of these
115. Which one of these is a tree based learner?
a. Bayesian classifier c. Random Forest
b. Bayesian Belief Network d. Rule based
116. Which of the following sentence is FALSE regarding reinforcement learning
a. It may be used for c. It discovers causal relationships.
b. It is used for d. It relates inputs to
117. A game can be formally defined as a kind of search problem with the following
components.
a. Terminal Test b. Successor Function c. All of these d. Initial State
118. Ability to think, puzzle, make judgments, plan, learn, communication by its own is
known as ___
a. None of these b. All Narrow AI c. All Super AI d. All General AI
119. A certain Professor at the Stanford University coined the word 'artificial intelligence'
in 1956 at a conference
a. John McCarthy b. David Levy b. Hans Berliner c. Joseph Weizenbaum
120. Inductive learning takes examples and generalizes rather than starting
with
a. Existing b. Deductive c. None of these d. Inductive
121. 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 mathematical functions that are continue
c. Because they are the only mathematical functions you can draw
d. Because they are the only class of problem that Perceptron can solve
successfully
122. Which network is more accurate when the size of training set between small to
medium?
a. K-means clustering b. RBF c. PNN/GRNN d. None of these
123. What are the advantages of Nearest neighbour alogo?
a. Training is very fast c. Can learn complex target functions
b. All of these d. Don't lose information
124. 190. Out of the two repeated steps in EM algorithm, the step 2 is _
a. the maximization step c. the optimization step
b. the normalization step d. the minimization step
125. What is needed to make probabilistic systems feasible in the world?
a. Crucial robustness b. Reliability c. Feasibility d. None of these
126. What of the following is considered to be a pivotal event in the history of AI.
Select one:
a. 1950, Computing Machinery and Intelligence.
b. 1949, Donald O, The organization of Behaviour.
c. 1961, Computer and Computer Sense.
d. 1956, Dartmouth University Conference Organized by John McCarthy.
127.Types of Naïve Bayes Model:
a. Gaussian b. Multinomial c. All of these d.
Bernoulli
129. 112 In k-NN algorithm, given a set of training examples and the value of k <
size of training set (n), the algorithm predicts the class of a test example to be the.
What is/are advantages of CBR?
a. Class of the closest
b. Most frequent class among the classes of k closest training
c. Least frequent class among the classes of k closest training
d. Most frequent class among the classes of the k farthest training
examples.
130. Cost complexity pruning algorithm is used in?
a. CART b. All of these c. ID3 d. 5
131. The core components are constituents of AI are derived from
a. All of these b. Cognition c. Computation d. Concept of logic
132. A term used to describe the case when the independent variables in a multiple
regression model are correlated is
a. Regression b. multicollinearity c. all false d. correlation
133. A Neural Network can answer
a. IF-The-Else Analysis Questions c. what-if questions
 b. For Loop questions d. None of these
134. The field that investigates the mechanics of human intelligence is:
a. cognitive science b. History c. sociology d. psychology
135. A different learning method does not include
a. Analogy b. Memorization c. Introduction d. Deduction
136. The average positive difference between computed and desired outcome
values.
a. mean squared error c. mean absolute error
b. root mean squared error d. mean positive error
137. A computer program that learns to play checkers might improve its
performance as:
a. None of these
b. Experience obtained by playing games against
c. Measured by its ability to win at the class of tasks involving playing checkers
d. Measured by its ability to win at the class of tasks involving playing
checkers and Experience obtained by playing games against
138. is any predicate (or its negation) applied to any set of terms.
a. Literal b. Clause c. None of these d. Null

139. ‘a I= 13 Ito mean that the sentence a entails the sentence 13) if and only if, in
every model in which a is 13 is also
a. True, true b. False, false c. True, false d. False, true
140.Which modifies the performance element so that it makes better decision?
Performance element
a. Learning element c. Changing element
b. Performance element d. None of these
141. All of the following are suitable problems for genetic algorithms EXCEPT
a. dynamic process control
b. simple optimization with few variables
c. pattern recognition with complex patterns
d. simulation of biological models
142. IBM Watson supercomputer comes under ____ AI.
a. General AI b. Narrow AI c. Neural AI d. None of these
143. Full form of MDL?
a. Minimum Description Length c. Minimum Domain Length
b. Maximum Description Length d. None of these
144. What are the advantages of neural networks over conventional computers? (F)
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. All of these c. Only (i) d. (I) and (iii) are
true
145. The first widely used commercial form of Artificial Intelligence (Al) is being
used in many popular products li
a. Fuzzy logic b. Boolean logic c. Human logic d. Functional
logic
146. The initial state and the legal moves for each side define the for the game.
a. State Space Search b. Game Tree c. Search Tree d. Forest
147. Which of the following will be true about k in k-NN in terms of variance
a. When you decrease the k the variance will increases
b. Can't say
 c. When you increase the k the variance will increases
d. None of these
148. The Candidate-Elimination Algorithm
a. Candidate-Elimination algorithm computes the description of this set without
explicitly enumerating all of its
b. This is accomplished by using the more-general-than partial ordering and
maintaining a compact representation of the set of consistent
c. The key idea in the Candidate-Elimination algorithm is to output a description
of the set of all hypotheses consistent with the training
d. All of these
149. General algorithm applied on game tree for making decision of win/lose is
a. MIN/MAX Algorithms C. Greedy Search Algorithms
b. DFS/BFS Search Algorithms D. Heuristic Search Algorithms
150. Chance Nodes are represented by which of the following
a. Squares b. Circles c. Triangles d. Solar street light

Internal Assessment

1. Which of the following sentences are true?

A. in pre-pruning a tree is pruned by halting its construction early
B. a pruning set of class labelled tuples is used to estimate cost complexity
C. the best pruned tree is the one that minimizes the number of encoding bits
D. all of the above

2. what are advantages of the neural network over conventional computers? (i) they have the
ability to learn by example (ii) they are more fault tolerant (iii) they are more suited for the
real time operation due to their high 'computational' rates
a) (i) and (ii) are true c) All of the these
b) (i) and (iii) are true d. Only (i)

3. the compactness of the bayesian network can be described by

a) Locally structuredc) Partial structure
b) Fully structured d) All of the mentioned

4. how the bayesian network can be used to answer any query

a) Full distribution c) Partial distribution
b) Joint distribution d) All of the mentioned

5. How fuzzy logic is different from conventional control method?

a) IF and THEN Approach
b) FOR Approach
c) WHILE Approach
d) DO Approach

6. examples of naive bayes algorithm is/are

a. Classifying articles
b. Spam filtration
c. Sentimental analysis
d. All of these

7. Which statement is true about prediction problems? *1 point

a. The output attribute must be categorical.
b. The output attribute must be numeric.
 c. The resultant model is designed to determine future outcomes.
d. The resultant model is designed to classify current behaviour.

8. what is heuristic function

a. A function whose return type is nothing
b. A function that maps from problem state descriptions to measures of desirability.
c. A function which takes parameters of type string and returns an integer value
d. A function to solve mathematical problems.

9. EM algorithm includes two repeated steps, here the step 2 is :

a. None of these c. the maximization step
b. The minimization step d. the normalization

The first mode attempts to estimate the missing or latent variables, called the estimation-step
or E-step.

10. Bayes' Theorem states that the relationship between probability of hypothesis before getting
the evidence P(H) and the probability of hypothesis after getting the evidence P(HIE) is
a. [P(E) P(H)] / P(EIH) C. [P(EIH)P(H)] / P(E)
b. [P(EIH)P(E)] / P(H) D. ALL FALSE

11. which condition is used to influence a variable directly by all the others
a) Partially connected
b) Fully connected
c) Local connected
d) None of the mentioned

12. which of the following statements about regularization is not correct?

a. Using too large a value of lambda can cause your hypothesis to overfit the data
b. Using too large a value of lambda can cause your hypothesis to underfit the data.
c. Using a very large value of lambda cannot hurt the performance of your hypothesis.
d. None of the above
13. what is/are advantages of cbr?
a. Knowledge is in a form understandable to human
b. All of these
c. A local approx. is found for each test case
d. Fast to train

14. 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

15. which search is equal to minimax search but eliminates the branches that cannot influence
the final decision
a) Depth-first search
b) Breadth-first search
c) Alpha-beta pruning
d) None of the mentioned

16. ____ AI is a hypothetical concept of AI.

A. All Narrow AI
B. All General AI
 C. All Super AI
D. None of the above

17. which is not familiar connectives in first order logic.

a. And b. not c. or d. iff

18. artificial intelligence has its expansion in the following application

a) Planning and Scheduling
b) Game Playing
c) Robotics
d) Planning and Scheduling, Game Playing, Robotics

19. how large is the hypothesis space when we have n Boolean attributes (|H|)
a. 3n
b. |H|
c. 2n
d. 4n
e. |H|
f. 1n
g. |H|

20. PAC stands for

a. Probably Approximate Correct
b. Probably Approx. Correct
c. Probably Approximate Computation
d. Probably Approx. Computation

21. choose the correct option. A. Knowledge base(kb is consists of set of statements. B)
inference is deriving a new sentence from the KB
a. A is true, B is true c. A is true, B is false
b. A is false, B is true d. A is false, B is false

22. fuzzy logic is usually represented as

a. none of these
b. both IF-THEN-ELSE rules and IF-THEN rules
c. IF-THEN rules
d. IF-THEN-ELSE rules

23. A subset of machine learning that involves systems that think and learn like humans using
artificial neural networks
a. all true b. Artificial Intelligence c. Deep Learning d. Machine Learning

24. Features of reinforcement learning

a. RL is training by reward and
b. RL is learning from trial and error with the
c. All of these
d. Set of problems rather than set of techniques

25. sensing organs as input mechanical movement organs as output and central nervous system
in brain as control and computing devices is known as _____ of human being
A. Information Control Paradigm
B. Information Processing Paradigm
C. Information Processing Control
D. None of the above
26. Learning that enables massive quantities of data is known as
a. Machine learning b. Artificial Intelligence c. Deep Learning d. all of these

27. A subset of machine learning that involves systems that think and learn like humans using
artificial neural networks
a. Machine learning b. Artificial Intelligence c. Deep Learning d. all of these

28. Naive Bayes algorithm is learning algorithm

a. Supervised b. unsupervised c. Reinforcement d. none of these

29. Artificial intelligence has its expansion in the following application

a. Planning and Scheduling b. Robotics c. Game playing
d. Planning and Scheduling, Game Playing, Robotics

30. why is the XOR problem exceptionally interesting to neural network researchers?
(a) Because it can be expressed in a way that allows you to use a neural network
(b) Because it is complex binary operation that cannot be solved using neural networks
(c) Because it can be solved by a single layer perceptron
(d) Because it is the simplest linearly inseparable problem that exists.

31. what are taken into account of state-space search

a. Postconditions b.Preconditions c. Effects
d. Both Preconditions & Effects

32. which values are independent in minimax search algorithm

a) Pruned leaves x and y
b) Every states are dependant
c) Root is independent
d) None of the mentioned

33. the concept derived from __ level are propositional logic, tautology, predicate calculus.
model temporal
A. Cognition level B. Logic level C. Functional level D. All of above

34. In a learning system the component that takes as input the history or trace of the game and
produces at output a set of training examples of the target function is known as
a. Critic b. performance system c. generalizer d. all of these

35. A perceptron adds up all the weighted inputs it receives, and if it exceeds a certain value, it
outputs a 1, otherwise it just outputs a 0
a. Can’t say c. sometimes- it ca also output intermediate values as well
b. True d. false

36. Symbols, symbolic expressions and computing with those is at the core of
A. LISP B. ELIZ C. PROLOG D. NLP

37. Bootstrapping allows us to

A. choose the same training instance several times.
B. choose the same test set instance several times.
C. build models with alternative subsets of the training data several times.
D. test a model with alternative subsets of the test data several times.

38. data used to build a data mining model

a. validation data b. training data c. test data d. hidden data
39. which of the following is not function of symbolic in the various function representation of
Machine Learning
a. Rules in first-order predicate logic
b. Decision Trees
c. Hidden-Markov Models (HMM)
d. Rules in propotional Logic

40. which of the following is not a necessary feature of a reinforcement learning solution to a
learning problem
a. exploration versus exploitation dilemma
b. representation of the problem as a Markov Decision process
c. learning based on rewards
d. trial and error approach to learning

41. What is an auto-associative network?

a) a neural network that contains no loops
b) a neural network that contains feedback
c) a neural network that has only one loop
d) a single layer feed-forward neural network with pre-processing

42. Uncertainty arises in the wumpus world because the agent’s sensors give only ___________
a) Full & Global information c) Partial & local Information
b) Partial & Global Information d) Full & local information

43. The ____ level contains constituents at the third level which are knowledge based system, heuristic
search, automatic theorem proving, multi-agent system.
A. Cognition level B. Gross level C. Functional level D. All of above

44. In general to have a well-defined learning problem, we must identify which of the following
a. the class of tasks c. the source of expectations
b. all of the above d. the measure of performance to be improved

45. what is false regarding regression?

a. It discovers causal relationships c. It is used for prediction.
b. It may be used for interpretation. D. It relates inputs to outputs.

46. correct (h) is the percent of all training examples correctly classified by hypothesis then fitness
function is equal to ------ > (correct(h))2

47. which of the following are the advantages 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 these

48. Aristotle's theory of syllogism and descartes and kant's critic of pure reasoning made knowledge on
a. Logic b. Computation logic c. all option true d, cognition logic

49. adding more basis functions in a linear model (pick the most probably option)
a. Decreases model bias
b. Decreases estimation bias
c. Decreases variance
d. Doesn’t affect bias and variance

50. which is true for Decision Theory?

 a. Probability theory + utility theory
b. Inference theory + utility theory
c. Uncertainty + utility theory
d. Probability theory + preference
e. Decision Theory

51. A computer program is said to learn from experience E with respect to some task T and some
performance measure P, if its performance at tasks in T, as measured by P, improves with experience
E.
a. Supervised learning problem
b. Well posed learning problem
c. All of these
d. Un-supervised learning problem
52. Computers are best at learning
a. Facts b. Concepts c. Procedures d. Principles

53. Google Alpha Go is an example of ____

A. Reactive machine C. Theory of mind
B. Limited memory D. None of the above

54. What are the advantages of Nearest neighbour alogo?

a. Training is very fast
b. Can learn complex target functions
c. Don’t lose information
d. All of these

55. what are two steps of tree pruning work

a. Pessimistic pruning and Optimistic pruning
b. Post pruning and the pre pruning
c. Cost complexity pruning and time complexity pruning
56. Features of ANN in which ANN creates its own organization or representation of information it
receives during learning time is
a. Self organization c. What-if Analysis
b. Adaptive Learning d. Supervised Learning

57. The quality of the result depends on (LWR)

a. Choice of the function
b. Choice of the kernel function K
c. Choice of the hypothesis space H
d. All of these

58. The values of the set membership is represented by

(a) Discrete Set (c) Probabilities
(b) Degree of truth (d) Both Degree of truth & ProbabilitiesRead

59. Communication between man and machine is related with

60. LISP
61. b) ELIZA
62. c) All of above
63. d) None of above
64. LISP
65. b) ELIZA
66. c) All of above
67.a. SIDA
d) None of above
b. ELIZA c. LISP d. SIPS

60. Father of Machine learning (ML)

a. Geoffrey Everest Hinton. B. Geoffrey Chaucer C. Geoffrey Hill

61. Machine learning is interested in the best hypothesis h from some space H, given observed training
data D. here best hypothesis means
e. Most general hypothesis
c. Most probable hypothesis
d. Most specific hypothesis
e. None of the Above

62.Which of the following is not numerical function in the various function representation of machine
learning
A. Neural Network C. Case-based
B. Support Vector Machines D. Linear Regression

63. Practical difficulties with Bayesian learning

a. Hypotheses make probabilistic predictions
b. Initial knowledge of many probabilities is required
c. No consistent hypothesis

64. Learning symbolic representations of concepts known as

a. Both a & b b. Artificial Intelligence c. Machine Learning

65. the sampling error is defined as

a. difference between sample and parameter
b. difference between population and sample
c. difference between population and parameter
d. difference between parameter and sample

66. Playing chess, purchasing suggestions on e-commerce site, self-driving cars, speech recognition
a. All Super AI b. All Narrow AI c. All General AI

67. The worldwide researchers are now focusing on developing machines with __ AI
a. All General AI b. All Super AI c. All Narrow AI

68. Fuzzy Set theory defines fuzzy operators. Choose the fuzzy operators from the following.
a) AND b) OR c) NOT d) All of the these
69. fraud detection, image classification, diagnostic and Customer Retention are applications
in which of the following
a. Supervised learning Classification c. Unsupervised learning Regression
b. Reinforcement learning d. Unsupervised learning Classification

70. what is/are advantage(s) of Locally Weighted Regression

a. Pointwise approximation of complex target function
b. Earlier data has no influence on the new ones
c. Both a & b
d. None of these

71. how will you counter over-fitting in decision tree?

a. By pruning the longer rules
b. By creating new rules
c. Both by pruning the longer rules and by creating new rules

72. how the effectiveness of the alpha-beta pruning gets increased?

a) Depends on the nodes
b) Depends on the order in which they are executed

73. genetic algorithm are a part of

a. Are adaptive heuristic search algorithm based on evolutionary ideas of natural
selection and genetics
b. Evolutionary Computing
c. All of these
d. Inspired by Darwin’s theory about evolution – ‘survival of the fittest’.

74. the field of study that gives computers the capability to learn without being explicitly
programmed
a. Artificial Intelligence b. Machine learning c. deep learning d. both a&b

75. in which of the following types of sampling the information is carried out under the
opinion of an expert
a) quota sampling c) purposive sampling
b) judgement sampling d) convenience sampling

76. the autonomous acquisition of knowledge through the use of computer programs is
called
a. Machine learning b. Artificial intelligence c. Deep Learning
77. which of the following is not numerical function in the various function representation of
machine learning
a. Case-based c. Neural Network
b. Linear Regression d. Support Vector Machines