1. Different learning methods does not include?

a. Analogy

b. Introduction

c. Memorization

d. Deduction

2. In language understanding, the levels of knowledge that does not include?

a. Syntactic

b. Empirical

c. Logical

d. Phonological

3. ML is a field of AI consisting of learning algorithms that?

a. At executing some task

b. All of the above

c. Over time with experience

d. Improve their performance

4. What is Machine learning?

a. The selective acquisition of knowledge through the use of computer programs

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

c. The autonomous acquisition of knowledge through the use of computer programs

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

5. What is true about Machine Learning.

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

b. All of the above

c. ML is a type of artificial intelligence that extract patterns out of raw data by using an algorithm or
method

d. The main focus of ML is to allow computer systems learn from experience without being explicitly
programmed or human intervention
6. 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

b. False

c. True

d. Sometimes – it can also output intermediate values as well

7. Chance Nodes are represented by __________

a. Squares

b. Circles

c. Disks

d. Triangles

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

a. Chance Nodes

b. All of the mentioned

c. End Nodes

d. Decision Nodes

9. Decision Nodes are represented by ____________

a. Circles

b. Disks

c. Triangles

d. Squares

10. Decision Trees can be used for Classification Tasks.

a. False

b. True
11. End Nodes are represented by __________

a. Disks

b. Triangles

c. Squares

d. Circles

12. How can learning process be stopped in backpropagation rule?

a. there is convergence involved

b. on basis of average gradient value

c. no heuristic criteria exist

d. none of the mentioned

13. Neural Networks are complex ______________ with many parameters.

a. Exponential Functions

b. Discrete Functions

c. Nonlinear Functions

d. Linear Functions

14. Signal transmission at synapse is a?

a. none of the mentioned

b. physical process

c. chemical process

d. physical & chemical both

15. The backpropagation law is also known as generalized delta rule, is it true?

a. yes

b. No
 16. The fundamental unit of network is

a. nucleus

b. neuron

c. brain

d. axon

17. What are dendrites?

a. none of the mentioned

b. fibers of nerves

c. other name for nucleus

d. nuclear projections

18. What are general limitations of back propagation rule?

a. slow convergence

b. scaling

c. all of the mentioned

d. local minima problem

19. What are the general tasks that are performed with backpropagation algorithm?

a. function approximation

b. all of the mentioned

c. prediction

d. pattern mapping

20. What is Decision Tree?

a. None of the mentioned

b. 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

c. Structure in which internal node represents test on an attribute, each branch represents outcome

d. Flow-Chart
 21. What is meant by generalized in statement “backpropagation is a generalized delta rule” ?

a. because delta is applied to only input and output layers, thus making it more simple and
generalized

b. because delta rule can be extended to hidden layer units

c. it has no significance

d. none of the mentioned

22. What is the objective of backpropagation algorithm?

a. to develop learning algorithm for single layer feedforward neural network

b. to develop learning algorithm for multilayer feedforward neural network

c. none of the mentioned

d. to develop learning algorithm for multilayer feedforward neural network, so that network can be
trained to capture the mapping implicitly

23. What is true regarding backpropagation rule?

a. all of the mentioned

b. error in output is propagated backwards only to determine weight updates

c. it is also called generalized delta rule

d. there is no feedback of signal at nay stage

24. What is true regarding backpropagation rule?

a. actual output is determined by computing the outputs of units for each hidden layer

b. none of the mentioned

c. hidden layers output is not all important, they are only meant for supporting input and output
layers

d. it is a feedback neural network

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

a. Worst, best and expected values can be determined for different scenarios

b. Possible Scenarios can be added

c. Use a white box model, If given result is provided by a model

d. All of the mentioned

26. _________ evolution over many generations was directly influenced by the experiences of individual
organisms during their lifetime

a. Baldwin

b. None of these

c. Lamarckian

d. Bayes

27. _________ is any predicate (or its negation) applied to any set of terms.

a. Clause

b. Literal

c. Null

d. None of these

28. ____________ emphasizes learning feedback that evaluates the learner's performance without
providing standards of correctness in the form of behavioural targets.

a. Reinforcement learning

b. None of these

c. Supervised Learning

29. 0*10 represents the set of bit strings that includes exactly

a. 0100, 0110

b. 0100, 0010

c. 0010, 0010

d. 0010, 0110
30. Correct ( h ) is the percent of all training examples correctly classified by hypothesis h. then
Fitness function is equal to

a. Fitness ( h) = (correct ( h)) 3

b. Fitness ( h) = (correct ( h)) 2

c. Fitness ( h) = (correct ( h)) 4

d. Fitness ( h) = (correct ( h))

31. Each schema the set of bit strings containing the indicated as

a. 0s, 1s

b. 0s, 1s, *s

c. only 0s

d. only 1s

32. Features of Reinforcement learning

a. Set of problem rather than set of techniques

b. RL is learning from trial and error with the world.

c. RL is training by reward and punishments.

d. All of these

33. GA techniques are inspired by _________ biology.

a. Cytology

b. Anatomy

c. Ecology

d. Evolutionary
 34. Genetic algorithm is a

a. Search technique used in computing to find true or approximate solution to optimization and
search problem

b. None

c. Sorting technique used in computing to find true or approximate solution to optimization and sort
problem

d. Both

35. Genetic operators includes

a. Mutation

b. Both

c. None

d. Crossover

36. Ground literal is a literal that

a. does not contains any functions

b. Contains only variables

c. does not contains any variables

d. Contains only functions

37. ILP stand for

a. Inductive Logical programming

b. Inductive Logic Programming

c. Inductive Logical Program

d. Inductive Logic Program

38. Produces two new offspring from two parent string by copying selected bits from each parent is
called

a. None of these

b. Crossover

c. Mutation
 d. Inheritance

39. Search through the hypothesis space cannot be characterized. Why?

a. Hypotheses are not created by crossover and mutation operators.

b. Hypotheses are created by crossover and mutation operators that allow radical changes between
successive generations

c. None

40. Statement: Genetic Programming individuals in the evolving population are computer programs
rather than bit strings.

a. True

b. False

41. The algorithm operates by iteratively updating a pool of hypotheses, called the

a. Population

b. Fitness

c. None

42. What is the correct representation of GA?

a. GA(Fitness, Fitness_threshold, p)

b. GA(Fitness, Fitness_threshold, p, r )

c. GA(Fitness, Fitness_threshold)

d. GA(Fitness, Fitness_threshold, p, r, m)

43. What is/are the requirement for the Learn-One-Rule method?

a. Output rule has a high accuracy but not necessarily a high coverage.

b. ALL

c. Output, delivers a single rule that covers many +ve examples and few -ve.

d. Input, accepts a set of +ve and -ve training examples.

 44. When would the genetic algorithm terminate?

a. Maximum number of generations has been produced

b. None

c. Both

d. Satisfactory fitness level has been reached for the population.

45. Which type of feedback used by RL?

a. Purely Instructive feedback

b. Purely Evaluative feedback

c. Both

46. What is back propagation?

a. None
b. It is the transmission of error back through the network to allow weights to be
adjusted so that the network can learn
c. It is another name given to the curvy function in the perceptron
d. It is another name given to the curvy function in the perceptron

47. What is perceptron?

a. An auto-associative neural network

b. A single layer feed-forward neural network with pre-processing
c. A neural network that contains feedback
d. A double layer auto-associative neural network

48. The Candidate-Elimination Algorithm represents the .

a. Solution Space
b. Elimination Space
c. Version Space
d. All
49. Which of the following is a disadvantage of decision trees?

a. Decision trees are prone to be overfit

b. Decision trees are robust to outliers
c. None
d. Factor analysis

50. Which of the following is not type of learning?

a. Supervised Learning
b. Semi-unsupervised Learning
c. Unsupervised Learning
d. Reinforcement Learning

51. Designing a machine learning approach involves:-

a. Choosing a representation for the target function

b. Choosing the type of training experience
c. Choosing the target function to be learned
d. Choosing a function approximation algorithm
e. All

52. Which of the following is not a supervised learning?

a. PCA
b. Decision Tree Answer
c. Naive Bayesian
d. Linear Regression

53. What is true regarding backpropagation rule?

a. it is also called generalized delta rule

b. all of the mentioned
c. error in output is propagated backwards only to determine weight updates
d. there is no feedback of signal at nay stage
 54. Inductive learning takes examples and generalizes rather than starting with

a. Existing
b. Deductive
c. Inductive
d. None

55. Inductive learning is based on the knowledge that if something happens a lot it is
likely to be generally

a. True
b. False Answer

56. FIND-S Algorithm starts from the most specific hypothesis and generalize it by
considering only

a. None
b. Negative
c. Positive
d. Negative or Positive

57. Neural Networks are complex functions with many parameter

a. Non linear
b. Discreate
c. Linear
d. Exponential

58. The Version space is:

a. The version space consists of only specific

b. None of these
c. 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
 59. Genetic Algorithm are a part of

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

60. Concept learning inferred a ______valued function from training examples of its input
and output.

a. Boolean
b. All
c. Hexadecimal
d. Decimal

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

a. Recurrent neural network

b. Perceptrons
c. Multi layered perceptron
d. Self organizing maps

62. Which is true for neural networks?

a. Node could be in excited state or non-excited state

b. Each node computes it‟s weighted input
c. All
d. It has set of nodes and connections
63. Concept learning is basically acquiring the definition of a general category from
given sample positive and negative training examples of the

a. False
b. True

64. Targetted marketing, Recommended Systems, and Customer Segmentation are

applications in which of the following

a. Reinforcement Learning
b. Unsupervised Learning: Regression
c. Unsupervised Learning: Clustering
d. Supervised Learning: Classification

65. Father of Machine Learning (ML)

a. Geoffrey Hill
b. None
c. Geoffrey Everest Hinton
d. Geoffrey Chaucer

66. Backpropagaion learning is based on the gradient descent along error surface.

a. False
b. True

67. Decision Tree is a display of an Algorithm?

a. False
b. True