MCQ suggestions for CA4 and SEMESTER EXAMINATION

1. The truth values of traditional set theory can be defined as _________ and that of fuzzy logic is
termed as _________.
a. Either 0 or 1, either 0 or 1. b. Between 0 & 1, either 0 or 1.
a. Either 0 or 1, between 0 & 1. d. Between 0 & 1, between 0 & 1.

2. _________ represents the fuzzy logic

a. IF-THEN rules
b. IF-THEN-ELSE rules
c. Both
d. None.

3. A perceptron can be defined as _________

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

4. Backpropagation can be defined as _________

a. It is another name given to the curvy function in the perceptron.
b. It is the transmission of errors 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 above

5.  What is the name of the network, which includes backward links from the output to the inputs
as well as the hidden layers?
a. Perceptron b. Self-organizing maps c. Multi-layered perceptron d. Recurrent neural
network

6. Which of the following fuzzy operators are not utilized in fuzzy set theory?
a. AND
b. OR
c. NOT
d. Ex-OR

7. Which of the following is not the promise of an artificial neural network?

a. It can survive the failure of some nodes
b. It can handle noise
c. It can explain the result
d. It has inherent parallelism

8. Which of the following is true for unsupervised learning?

a. Some specific output values are disclosed

b. Some specific output values aren't disclosed
c. No relevant inputs value is specified
d. Both inputs as well outputs are specified

9. Automated vehicle is an application of _________

a. Unsupervised learning
b. Supervised learning
c. Reinforcement learning
d. Active learning

10. Which of the following models are utilized for learning?

a. Neural networks
b. Decision trees
c. Propositional and FOL rules
d. All of the above

11. Feature of ANN in which ANN creates its own organization of representation of information
it receives during learning time is

a. Adaptive Learning
b. What-if analysis
c. Self-Organization
d. Supervised learning

12. In artificial neural network, interconnected processing elements are termed as _________

a. Weights
b. Nodes or neurons
c. Axon
d. Soma
13. What is the name of the process that represents modified elements of the DNA?

a. Selection

b. Mutation

c. Recombination

d. None of the above

14. What is the name of the operator that is functioned on the population?

a. Recombination
b. Reproduction
c. Mutation
d. None of the above

15.  In how many steps does a crossover operator proceed?

a. 2
b. 3
c. 4
d. 5

16. Which of the following best relate to reinforcement learning?

a. Error based learning

b. Backpropagation learning
c. Output-based learning
d. None of the above

17. ________ deals with uncertainty problems with its own merits and demerits

a. Neuro-fuzzy
b. Neuro-genetic
c. Fuzzy-genetic
d. None

18. What does FAM stand for?

a. Fuzzy Association Memory
b. Fuzzy Associative Memory
c. Fuzzy Assist Memory
d. None of the above

19. Which of the following exhibits non-linear functions to any desired degree of accuracy?

a. Neuro-fuzzy
b. Neuro-genetic
c. Fuzzy-genetic
d. None of the above

20. Soft computing is used to solve:

1. Liner issues
2. Non-linear issues
3. Both 1 and 2
4. None of the above
21.  In supervised learning models are trained on:

1. Unlabelled data
2. Labelled data
3. Half labelled data – half unlabelled
4. None of the above
22. Out of hard computing and soft computing which one takes more time for
computation?

1. Soft computing
2. Hard computing
3. Both takes almost same time
4. None of the above
23. One human cell contains how many pairs of chromosomes?

1. 21
2. 22
3. 23
4. 24
24. The entire combination of genes is called:

1. Phenotype
2. Genotype
3. Allele
4. None of the above
25.  How can uncertainty be represented?
a. Fuzzy logic
b. Probability
c. Entropy
d. All of the above
26. The name of the operator that is present in fuzzy set theory, that is linguistic in nature, is:
a. Hedges
b. Lingual Variable
c. Fuzz Variable
d. All of the above

27. How many levels of fuzzifier is there?

a.3
b.4
c.5
d.6
28. The intersection of two fuzzy sets is the ______ of each element from two sets

A. maximum

B. minimum

C. equal to

D. not equal to

29.  
Core of soft Computing is

A.Fuzzy Computing, Neural Computing, Genetic Algorithms

B.Fuzzy Networks and Artificial Intelligence

C. Artificial Intelligence and Neural Science

D.Neural Science and Genetic Science

30.  
Who initiated the idea of Soft Computing

A.Charles Darwin

B.Lofti A Zadeh

C. Rechenberg

D.Mc_Culloch
31.  
Neural Computing

A.mimics human brain

B.information processing paradigm

C. Both (a) and (b)

D.None of the above

32.  
Genetic Algorithm are a part of

A.Evolutionary Computing

B.inspired by Darwin's theory about evolution - "survival of the fittest"

C. are adaptive heuristic search algorithm based on the evolutionary ideas of natural
selection and genetics

D.All of the above

33. Which of the following is considered while determining the nature of the learning problem?
1. Feedback
2. Problem
3. Environment
4. All of the above
34. Which of the following is associated with fuzzy logic?
1. Many-valued logic
2. Crisp set logic
3. Binary set logic
4. Two-valued logic
35. A 4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the constant
of proportionality being equal to 2. The inputs are 4, 10, 5 and 20 respectively. The output will
be:

a)238
b) 76
c) 119
d) 123
36. If a fuzzy relation is reflexive, symmetric and transitive then it is known as _________________
a) Partial order
b) Equivalence
c) Both
d) None
37. A total order relation must be a __________ relation with some other characteristics.
a) Partial order
b) Equivalence
c) Both
d) None
38. Adaptive linear element is known as ____________
a) Adliele
b) Adaline
c) Both
d) None
39. Which is not expressed in linear separable problem category
a) AND
b) NAND
c) OR
d) X-OR
40. Jordan network is ___________________
a) SLFFNN
b) MLFFNN
c) Recurrent neural network
d) None
41. ________________ units are used to produce feedback in Elman network
a) Input
b) Output
c) Hidden
d) None
42. Example of Bio-Inspired computing ________________
a) ACO
b) PSO
c) Bug algorithm
d) All of the above
42. Which of the following operation is responsible to jump from one hill to another hill?
1. Mutation
2. Cross Over
3. Fitness Function
4. Natural Selection
43.
Which of the following statement is/are true?
A) Encoding, Fitness Function, Selection, Crossover, Mutation are Genetic Algorithms features.
B) Crossover operator defines how chromosomes of parents are mixed in order to obtain genetic
codes of their offspring.
1. Statement A True and Statement B True
2. Statement A True and Statement B False
3. Statement A False and Statement B True
4. Statement A False and Statement B False
44. Consider the following:
(a) Evolution
(b) Selection
(c) reproduction
(d) Mutation
1. (b), (c) and (d) only
2. (b) and (d) only
3. (a), (b), (c) and (d)
4. (a), (b) and (d) only

45.  What is not true about heuristics?

a. Learning by self-experience
b. useful at primary level of experience
c. Involves problem solving
d. Students are active throughout learning process

46. Ability to learn how to do tasks based on the data given for training or initial
experience

A.Self Organization

B.Adaptive Learning

C. Fault tolerance

D.Robustness

47. Which of the following produces hypotheses that are easy to read for humans?
a) Machine Learning
b) ILP
c) First-order logic
d) Propositional logic
48. Which of the following is termed exploratory learning?

a. Active learning
b. Supervised learning
c. Reinforcement learning
d. Unsupervised learning

49. What is the name of the process that represents modified elements of the DNA?

a. Selection
b. Mutation
c. Recombination
d. None of the above

50.  What is the name of the operator that is functioned on the population?

a. Recombination
b. Reproduction
c. Mutation
d. None of the above

51.  Which of the following is not a specified method used for selecting the parents?

a. Tournament Selection
b. Steady-state
c. Elitism
d. Boltzmann selection

52. Which of the following exhibits non-linear functions to any desired degree of accuracy?

a. Neuro-fuzzy
b. Neuro-genetic
c. Fuzzy-genetic
d. None of the above

53. Matrix crossover is also known as _________

a. One dimensional
 b. Two dimensional
c. Three dimensional
d. None of the above

54.  The ________ causes all the bits in the first operand to shift to the left by the number of
positions indicated by the second operand.

a. Shift right
b. Shift left
c. Shift operator
d. None of the above

55. What is soft  computing?

In computer science, soft computing is the use of inexact solutions to computationally hard
tasks such as the solution of NP-complete problems, for which there is no known algorithm that
can compute an exact solution in polynomial time.

56. Name some soft computing techniques

Neural Networks, Support Vector Machine, Fuzzy Logic, Evolutionary Algorithm, Genetic
Algorithm, Machine Learning (ML) and Probabilistic Reasoning (PR), Antcolony optimization,
Particle swarm optimization, cuckoo search algorithm
57. Define Hard computing.

Hard Computing is that the ancient approach employed in computing that desires associate in
nursing accurately declared analytical model.

58. Soft computing is stochastic in nature - True/False?

True

59. Hard computing produces precise results - True/False?

True.

60. Define machine learning.

Machine learning is a branch of artificial intelligence (AI) which focuses on the use of data and
algorithms to imitate the way that humans learn, gradually improving its accuracy.
61. An approximation based fast solution system can implemented using fuzzy logic – t/f
T

62. Fuzzification?
Convert crisp values into fuzzy value.
63. Defuzzification is the process of converting _________ values into _______ values.
fuzzy , crisp

64. What are the limitations of Fuzzy system?

It is a rule based system rather than based on definite mathematical expression. Therefore
solution is obtained using deductive reasoning which may not be exact solution.

65. What is cardinality of a Fuzzy set?

The cardinality of a fuzzy set A, the so-called SIGMA COUNT, is expressed as a SUM of the values
of the membership function of A.

66. What is an empty Fuzzy set?

A fuzzy set A is empty, IF AND ONLY IF: μA(x) = 0, ∀x∈X

67. What is Fuzzy compliment?

The membership function of the Complement of a Fuzzy set A with membership function ‘μA’ is
defined as the negation of the specified membership function. This is called the negation
criterion. The Complement operation in Fuzzy set theory is the equivalent of the NOT operation
in Boolean algebra.

68. What do you mean by height of a Fuzzy set?

The height of a fuzzy set A is the largest membership grade of an element in A height(A) =
maxx(μA(x)).

69. Define a Fuzzy Cartesian product.

Let A be a fuzzy set on universe X and B is a fuzzy set on universe Y . The Cartesian product
between A and B will result in a fuzzy relation such that A x B = R ∈ X x Y , where R has a
membership μR (x,y) = min [ μA (x) , μB (y) ]

70. What do mean by Fuzzy logic controller?

By a fuzzy logic controller (FLC) we mean a control law that is described by a knowledge-based
system consisting of IF...THEN rules with vague predicates and a fuzzy logic inference
mechanism.

71. What do you mean by NN architecture ?

The arrangement of neurons into layers and the connection pattern within and between layers
is called the NN architecture .

72. What is learning rate?

Denoted by α.Used to control the amount of weight adjustment at each step of training.

73. Is it acceptable to initialize weight vectors in self organizing map to random un-normalized

values .Justify in a few lines.
It is not acceptable to use un-normalized initial weight vectors since Euclidean distance is
calculated to determine the winning unit.

74. What is associative memory?

A neural network that is trained to associate a set of input vectors with a corresponding set of
output vectors is called associative memory.
75. What is auto associative memory?
If the desired output vector is same as the input vector, the network is an auto associative
memory.

76. What is hetro-associative memory?

If the desired output vector is different from the input vector, the net is an hetro-associative
memory.

77. What is Counter Propagation Network(CPN)?

Defined by Robert Hecht -Nielsen in 1986, CPN is a network that learns a bidirectional
mapping in hyper dimensional space.