SOFT COMPUTING MCQS
1. Conventional Artificial Intelligence is different from soft computing in the sense
Conventional Artificial Intelligence deal with predicate logic where as soft computing deal with fuzzy logic
Conventional Artificial Intelligence methods are limited by symbols where as soft computing is based on empirical data
Both (a) and (b)
None of the above
ANS: C BOTH A AND B
2. Machine learning is
The autonomous acquisition of knowledge through the use of computer programs
The autonomous acquisition of knowledge through the use of manual programs
The selective acquisition of knowledge through the use of computer programs
The selective acquisition of knowledge through the use of manual programs
ANS : The autonomous acquisition of knowledge through the use of computer programs
3. How many types of agents are there in artificial intelligence?
1 2
3 4
ANS: 4
Reflex Agents.
Goal-Based Agents.
Utility-Based Agents.
Learning Agent.
A simple-reflex agent selects actions based on the agent's current perception of the world and not based on past perceptions. It can handle a full observation environment.
A model-based-reflex agent is designed to deal with partial accessibility. They do this by keeping track of the part of the world it can see now. It does this by keeping an internal state that depends on what it has seen before so it holds information on the unobserved aspects of the current state. It can handle a partial observation environment.
4. Fuzzy Computing
a.mimics human behavior b. deal with multi valued logic
c. deals with information which is vague, imprecise, uncertain, ambiguous, inexact, or probabilistic d. All of these
ANS: C
5. Let A and B are two fuzzy sets with membership function μ, then μ A∪B( x ) is equal to
a. μ A( x ) + μ B( x ) b. μ A( x ) - μ B( x )
c. MAX { μ A( x ) , μ B( x )} d. MIN { μ A( x ) , μ B( x )}
C
6. Consider the fuzzy set A given by, A = { 0 / 0·4 + 1 / 0·6 + 3 / 0·9 } then cardinality of A will be 0.4+0.6+0.9
a. 0 b. 4.0
c. 1.0 d. 1.9
D
7. The room temperature is hot. Here the hot (use of linguistic variable is used can be)
a. Fuzzy set b. Crisp set
c.sub set d. None of these.
A
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
a
2. Machine learning is
a. The autonomous acquisition of knowledge through the use of manual programs
b. The autonomous acquisition of knowledge through the use of computer programs
c. The selective acquisition of knowledge through the use of computer programs
d. None of these
b
3. Fuzzy Computing
a. mimics human behavior
b. does deal with multi valued logic
c.deals with information which is vague, imprecise, uncertain, ambiguous, inexact, or probabilistic
d.All of these
d
4. The values of the set membership is represented by
a. Discrete Set b.Degree of truth
c. Probabilities d.Both Degree of truth & Probabilities
ans: Both Probabilities and degree of truth ranges between 0 - 1.
5. Let A normal fuzzy set is one whose one membership function has
a. at least one element x in the universe whose membership value is 1 b. all elements in the universe have membership value of 1.
c. none of the elements in the universe has membership value of 1. d. at least one element x in the universe whose membership value is 0.
a
6. A fuzzy number is a fuzzy set with the property of
a. only normal b. only convex
c. both normal and convex
d. normal but not convex.
ans: c
7. A fuzzy set wherein no membership function has its value equal to 1 is called
a. subnormal fuzzy sets
b. normal fuzzy set
c. convex fuzzy set
d. concave fuzzy set
a
8. A fuzzy set has a membership function whose membership values are strictly monotonically increasing or strictly monotonically decreasing or strictly monotonically increasing than strictly monotonically decreasing with increasing values for elements in the universe
Normal
Subnormal
Convex
Concave
c
1st decrese then increaae hola -> concave hoto.
9. A fuzzy set wherein no membership function has its value equal to 1 is called
a. subnormal fuzzy sets
b. normal fuzzy set
c. convex fuzzy set
d. concave fuzzy set
a
10. If A and B are two fuzzy sets with membership functions:
μa(χ) ={0.2,0.5.,0.6,0.1,0.9} ,μb (χ)= {0.1,0.5,0.2,0.7,0.8}then the value of μa ∩ μb will be
{0.2,0.5,0.6,0.7,0.9}
{0.2, 0.5,0.2, 0.1,0.8}
{0.1, 0.5, 0.6, 0.1,0.8}
{0.1, 0.5, 0.2, 0.1,0.8}
d
intersection -> minimum
union -> maximum
11. The height h(A) of a fuzzy set A is defined as h(A) = sup A(x)
h(A) = 0
h(A) <0
h(A)=1
h(A)<1
c
base hola a hoto,
12. In propositional logic P ⇔ Q is equivalent to (Where ~ denotes NOT):
~ (P ˅ Q) ˄ ~ (Q ˅ P)
(~ P ˅ Q) ˄ (~ Q ˅ P)
(P ˅ Q) ˄ (Q ˅ P)
~ (P ˅ Q) → ~ (Q ˅ P)
b
13. Membership function can be thought of as a technique to solve empirical problems on the basis of
knowledge
examples
learning
experience
d
empirical problems hola d
14. Neural Computing
mimics human brain
information processing paradigm
both a and b
None of these
ANS : C
15. What are the 2 types of learning
Improvised and un-improvised
supervised and unsupervised
Layered and unlayered
None of these
ANS: B
16. Supervised Learning is
learning with the help of examples
learning without teacher
learning with the help of teacher
learning with computers as supervisor
ANS: C
What is composed of large number of highly interconnected processing elements (neurons) working in unison to solve problems.
ANN Perceptron
neuron None of these
A
Artificial neural network used for
Pattern Recognition Classification
Clustering All of these
All
A Neural Network can answer
a. For Loop questions b. what-if questions
c. IF-Then-Else Analysis Questions d. None of these
C
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
B
When the cell is said to be fired
a. if potential of body reaches a steady threshold values b.if there is impulse reaction
c. during upbeat of heart d. none of these
A
In artificial Neural Network interconnected processing elements are called
a.nodes or neurons b. weights
c. axons d. Soma
A
Each connection link in ANN is associated with ____ which has information about the input signal.
a. neurons b. weights
c. bias d. activation function
B
which is called Internal state of neuron that is the function of the inputs the neurons receives
a. Weight b. activation or activity level of neuron
c. Bias d. None of these
B
How many signal(s) can Neuron send at a time?
a. multiple b. 1
c. 2 d. None of these
B
The values of the set membership is represented by
Discrete Set
Degree of truth
Probabilities
Both Degree of truth & Probabilities
b
The boundary of the fuzzy A set is defined by those elements x of the universe such that
μA ( x ) = 1
μA ( x ) = 0
0 < μA ( x ) < 1
0 ≤ μA ( x ) ≤ 1.
d
Let A normal fuzzy set is one whose one membership function has
a. at least one element x in the universe whose membership value is 1
b. all elements in the universe have membership value of 1.
c. none of the elements in the universe has membership value of 1.
d. at least one element x in the universe whose membership value is 0.
a
Let A and B are two fuzzy sets with membership function μ, then μ A∪B( x ) is equal to
a. μ A( x ) + μ B( x )
b. μ A( x ) - μ B( x )
c. MAX { μ A( x ) , μ B( x )}
d. MIN{ μ A( x ) , μ B( x )}
c
The proposition logic lacks the ability to symbolize
quantification
connectivity
equivalence
Negation
c
Consider the fuzzy set A given by, A = { 0 / 0·4 + 1 / 0·6 + 3 / 0·9 } then cardinality of A will be 0.4+0.6+0.9
0
4.0
1.0
1.9
d
Fuzzy logic is usually represented as
IF-THEN-ELSE rules
IF-THEN rules
Both IF-THEN-ELSE rules & IF-THEN rules
None of these
b
__________________ is/are the way/s to represent uncertainty.
Fuzzy Logic
Probability
Entropy
All of these
d
The membership functions are generally represented in
Tabular Form
Graphical Form
Mathematical Form
Logical Form
b
Three main basic features involved in characterizing membership function are
Intuition, Inference, Rank Ordering
Fuzzy Algorithms, Neural network, Genetic Algorithm
Core, Support , Boundary
Weighted Average, center of Sums, Median
c
In supervised learning
a. classes are not predefined b. classes are predefined
c. classes are not required d. classification is not done
b
What is composed of large number of highly interconnected processing elements (neurons) working in union to solve problems.
a. ANN b. Perceptron
c. neuron d. None of these
a
Artificial neural network used for
a. Pattern Recognition b. Classification
c. Clustering d. All of these
d
In artificial Neural Network interconnected processing elements are called
a. nodes or neurons b. weights
c. axons d. Soma
a
Each connection link in ANN is associated with ________ which has information about the input signal.
a. neurons b. weights
c. bias d. activation function
b
Kohonen network / adaptive resonance theory model is
a. purely unsupervised
b. supervised
c. reinforcement
d. none of these.
a
In ANN model
a. learning constant should be small
b. should be constant throughout the epoch
c. should be ‘one’
d. Should be small but adaptive and remain stable to irrelevant input.
d
Expert systems
a. Combining different types of method or information
b. Approach to the design of learning algorithms that is structured along the lines of the theory of evolution
c.Decision support systems that contain an information base filled with the knowledge of an expert formulated in terms of if-then rules.
d. None of these
c
Every fuzzy complement has at most
a.two equilibrium b. three equilibrium
c.one equilibrium d.None of these
c
The boundary of the fuzzy A set is defined by those elements x of the universe such that
a.μA ( x ) = 1 b.μA ( x ) = 0
c.0 < μA ( x ) < 1 d. None of these
c
c. Let A and B are two fuzzy sets with membership function μ, then μ A∪B( x ) is equal to
μ A( x ) + μ B( x )
b. μ A( x ) - μ B( x )
c. MAX { μ A( x ) , μ B( x )}
d. MIN { μ A( x ) , μ B( x )}
c
Consider the fuzzy set A given by, A = { 0 / 0·4 + 1 / 0·6 + 3 / 0·9 } then cardinality of A will be 0.4+0.6+0.9
0 4.0
1.0 1.9
1.9
A __________ point of a fuzzy set A is a point x ∈ X at which µA(x) = 0.5
Core Support
Cross-over α - cut
cross-over
Membership function can be thought of as a technique to solve empirical problems on the basis of
knowledge examples
learning experience
ans: experience
A fuzzy set wherein no membership function has its value equal to 1 is called
a. subnormal fuzzy sets b. normal fuzzy set
c. convex fuzzy set d. concave fuzzy set
c
Supervised Learning is
a. learning with the help of examples b.learning without teacher
c. learning with the help of teacher
d. learning with computers as supervisor
c
Unsupervised learning is
a. learning without computers
b.problem based learning
c.learning from environment
d.learning from teachers
c
In supervised learning
a.classes are not predefined
b.classes are predefined
c.classes are not required
d.classification is not done
b
Artificial neural network used for
a. Pattern Recognition b.Classification
c. Clustering d. All of these
d
When the cell is said to be fired
a. if potential of body reaches a steady threshold values
b. if there is impulse reaction
c. during upbeat of heart
d. None of these
a
In artificial Neural Network interconnected processing elements are called
a. nodes or neurons b. weights
c. axons d. Soma
a
soma-> cell body -> forward information
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
b
which is called Internal state of neuron that is the function of the inputs the neurons receives
a. Weight
b. activation or activity level of neuron
c. Bias
d. None of these
b
What is composed of large number of highly interconnected processing elements (neurons) working in unison to solve problems.
ANN Perceptron
neuron None of these
ann
Artificial neural network used for
Pattern Recognition Classification
Clustering All of these
d
A Neural Network can answer
a. For Loop questions b. what-if questions
c. IF-Then-Else Analysis Questions
d. None of these
b
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
b
When the cell is said to be fired
a. if potential of body reaches a steady threshold values
b.if there is impulse reaction
d. none of these
c. during upbeat of heart
A
In artificial Neural Network interconnected processing elements are called
a.nodes or neurons b. weights
c. axons d. Soma
a
Each connection link in ANN is associated with ________ which has information about the input signal.
a. neurons b. weights
c. bias d. activation function
b
which is called Internal state of neuron that is the function of the inputs the neurons receives
a. Weight b. activation or activity level of neuron
c. Bias d. None of these
b
which is called Internal state of neuron that is the function of the inputs the neurons receives
c. activation or activity level of neuron
d. None of these
a. weight b. bias
c
Artificial neural network is based on the concept
a. gradient descent technique b. random descent technique
c. biological neuron
d. (a) and (c).
d
Kohonen network / adaptive resonance theory model is
purely unsupervised supervised
reinforcement
none of these.
c
The values of the fuzzy set membership is represented by ___________
a) Discrete Set
b) Degree of truth
c) Probabilities
d) Both Degree of truth & Probabilities
d
Fuzzy logic is usually represented as ___________
a) IF-THEN-ELSE rules
b) IF-THEN rules
c) Both IF-THEN-ELSE rules & IF-THEN rules
d) None of the mentioned
b
What is the form of Fuzzy logic?
a) Two-valued logic
b) Crisp set logic
c) Many-valued logic
d) Binary set logic
c
***************************************************************************
***************************************************************************
1. 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
ans: a
2. Who initiated the idea of Soft Computing
a. Charles Darwin
b. Lofti A Zadeh
c. Rechenberg
d. Mc_Culloch
ans: b
3. Conventional Artificial Intelligence is different from soft computing in the sense
a. Conventional Artificial Intelligence deal with predicate logic whereas soft computing deal with fuzzy logic
b. Conventional Artificial Intelligence methods are limited by symbols where as soft computing is based on empirical data
c. Conventional Artificial Intelligence deal with predicate logic whereas soft computing deal with fuzzy logic and Conventional Artificial Intelligence methods are limited by symbols where as soft computing is based on empirical data
d. None of these
ans: c
4. Machine learning is
a. The autonomous acquisition of knowledge through the use of computer programs
b. The autonomous acquisition of knowledge through the use of manual programs
c. The selective acquisition of knowledge through the use of computer programs
d, The selective acquisition of knowledge through the use of manual programs
ans: a
5. How many types of agents are there in artificial intelligence?
1 2 3 4
ans: 4
7. Fuzzy Computing mimics human behavior does deal with multi valued logic deals with information which is vague, imprecise, uncertain, ambiguous, inexact, or probabilistic All of these
Ans: All of these
8. The values of the set membership is represented by Discrete Set Degree of truth Probabilities Both Degree of truth & Probabilities
Ans:Degree of truth
9. Let’s assume that a fuzzy set A is defined as follows: A = 0·1/50 + 0·3/60 + 0·5/70 + 0·8/80 + 1/90 + 1/100. What will be the value of | A |? 3.7 6 1.7 None of these.
ans: 3.7
10. Every fuzzy complement has at most two equilibrium three equilibrium one equilibrium None of these.
ans: one equilibrium
11. The boundary of the fuzzy A set is defined by those elements x of the universe such that μA ( x ) = 1 μA ( x ) = 0 0 < μA ( x ) < 1 0 ≤ μA ( x ) ≤ 1.
ans: 0 ≤ μA ( x ) ≤ 1.
12. Let A normal fuzzy set is one whose one membership function has at least one element x in the universe whose membership value is 1 all elements in the universe have membership value of 1. none of the elements in the universe has membership value at least one element x in the universe whose membership value is 0. of 1.
ans: at least one element x in the
universe whose membership
value is 1
13. A fuzzy number is a fuzzy set with the property of only normal only convex both normal and convex normal but not convex.
ans:both normal and convex
14. Let A and B are two fuzzy sets with membership function μ, then μ A∪B( x ) is equal to μ A( x ) + μ B( x ) b. μ A( x ) - μ B( x ) c. MAX { μ A( x ) , μ B( x )} d. MIN { μ A( x ) , μ B( x )}
ans: c. MAX { μ A( x ) , μ B( x )}
15. The proposition logic lacks the ability to symbolize quantification connectivity equivalence Negation.
ans: Negation.
16. Consider the fuzzy set A given by, A = { 0 / 0·4 + 1 / 0·6 + 3 / 0·9 } then cardinality of A will be 0.4+0.6+0.9 0 4.0
1.0 1.9
ans:1.9
17. Fuzzy logic is usually represented as IF-THEN-ELSE rules IF-THEN rules Both IF-THEN-ELSE rules & IF-THEN rules None of these
ans: IF-THEN rules
18. __________________ is/are the way/s to represent uncertainty. Fuzzy Logic Probability Entropy All of these
ans:All of these
19. The membership functions are generally represented in Tabular Form Graphical Form Mathematical Form Logical Form
ans: Graphical Form
20. What is the form of Fuzzy logic Two-valued logic Crisp set logic Many-valued logic Binary set logic
ans:Many-valued logic
21. Three main basic features involved in characterizing membership function are Intuition, Inference, Rank Ordering Fuzzy Algorithms, Neural network, Genetic Algorithm Core, Support , Boundary Weighted Average, center of Sums, Median
ans: Core, Support , Boundary
22. The region of the universe that is characterized by complete membership in the set is called Core Support Boundary Fuzzy
ans: Core
23. A fuzzy set whose membership function has at least one element x in the universe whose membership value is unity is called sub normal fuzzy sets normal fuzzy set convex fuzzy set concave fuzzy set
ans: normal fuzzy set
24. Which of the following is used for probability theory sentences; Conditional logic logic propositional logic None of these
ans: propositional logic
25. Fuzzy set theory defines fuzzy operators. Choose the fuzzy operators from the following - AND OR NOT All of these
ans: All of these
26. What is meant by probability density function probability distributions Continuous variable discrete variable probability distributions for Continuous variables
ans: probability distributions for Continuous variables
27. The room temperature is hot. Here the hot (use of linguistic variable is used can be) Fuzzy set Crisp set sub set None of these.
ans: Fuzzy set
28. How many types of random variables are available 1 2 3 4
ans: 2
29. The truth values of traditional set theory is Either 0 or 1 0 1 None of these
ans: Either 0 or 1
30. Fuzzy logic is a form of Two valued logic Crisp set logic Many valued logic Binary set logic
ans: Many valued logic
31. There are also other operators, more linguistic in nature, called __________ that can be applied to fuzzy set theory. Hedges Lingual Variable Fuzzy Variable None of these
ans: Hedges
32. In propositional logic P ⇔ Q is equivalent to (Where ~ denotes NOT): ~ (P ˅ Q) ˄ ~ (Q ˅ P) (~ P ˅ Q) ˄ (~ Q ˅ P) (P ˅ Q) ˄ (Q ˅ P) ~ (P ˅ Q) → ~ (Q ˅ P)
ans: (~ P ˅ Q) ˄ (~ Q ˅ P)
33. Consider a fuzzy set A defined on the interval X = [0, 10] of integers by the membership function μA(x) = x / (x+2) ,Then the α cut corresponding to α = 0.5 will be {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10} {1, 2, 3, 4, 5, 6, 7, 8, 9, 10} {2, 3, 4, 5, 6, 7, 8, 9, 10} None of these
ans: {2, 3, 4, 5, 6, 7, 8, 9, 10}
34. If A and B are two fuzzy sets with membership functions: μa(χ) ={0.2,0.5.,0.6,0.
1,0.9} ,μb (χ)= {0.1,0.5,0.2,0.7,0.8}then the value of μa ∩ μb will be {0.2,0.5,0.6,0.7,0.9} {0.2, 0.5,0.2, 0.1,0.8} {0.
1, 0.5, 0.6, 0.1,0.8} {0.1, 0.5, 0.2, 0.1,0.8}
ans: {0.1, 0.5, 0.2, 0.1,0.8}
35. The height h(A) of a fuzzy set A is defined as h(A) = sup A(x) h(A) = 0 h(A) <0 h(A)=1 h(A)<1
ans: h(A)=1
36. A __________ point of a fuzzy set A is a point x ∈ X at which µA(x) = 0.5 Core Support Cross-over α - cut
ans: Cross-over
37. What are the following sequence of steps taken in designing a fuzzy logic machine? Fuzzification → Rule evaluation → Defuzzification Fuzzification → Defuzzification → Rule evaluation Rule evaluation → Fuzzification → Defuzzification Rule evaluation → Defuzzification → Fuzzification
ans: Fuzzification → Rule evaluation
→ Defuzzification
38. Membership function defines the fuzziness in a fuzzy set irrespective of the elements in the set, which are discrete or continuous. discrete or continuous continuous discrete None of these
ans: discrete or continuous
39. Membership function can be thought of as a technique to solve empirical problems on the basis of knowledge examples learning experience
ans: experience
41. In a Fuzzy set a prototypical element has a value 1 0 infinite None of these
ans: 1
42. A fuzzy set wherein no membership function has its value equal to 1 is called subnormal fuzzy sets normal fuzzy set convex fuzzy set concave fuzzy set
ans: subnormal fuzzy sets
43. A fuzzy set has a membership function whose membership values are strictly monotonically increasing or strictly monotonically decreasing or strictly monotonically increasing than strictly monotonically decreasing with increasing values for elements in the universe subnormal fuzzy sets normal fuzzy set convex fuzzy set concave fuzzy set
ans: convex fuzzy set
44. The membership values of the membership function are nor strictly monotonically increasing or decreasing or strictly monotonically increasing then decreasing subnormal fuzzy sets non convex fuzzy set convex fuzzy set concave fuzzy set
ans: non convex fuzzy set
45. The crossover points of a membership function are defined as the elements in the universe for which a particular fuzzy set has values equal to 1 0 infinite None of these
ans: None of these
46. The truth values of traditional set theory is ____________ and that of fuzzy set is __________ Either 0 or 1, between 0 & 1 Between 0 & 1, either 0 or 1 Between 0 &
1, between 0 & 1 Either 0 or 1, either 0 or 1
ans: Either 0 or 1, between 0 & 1
47. Neural Computing mimics human brain information processing paradigm both a and b None of these
ans: both a and b
48. Perceptron learning, Delta learning and LMS learning are learning methods which falls under the category of Error correction learning - learning with a teacher Reinforcement learning - learning with a critic Hebbian learning Competitive learning - learning without a teacher
ans: Error correction learning - learning with a teacher
49. What are the 2 types of learning Improvised and un-improvised supervised and unsupervised Layered and unlayered None of these
ans: supervised and unsupervised
50. Supervised Learning is learning with the help of examples learning without teacher learning with the help of teacher learning with computers as supervisor
ans: learning with the help of teacher
51. Unsupervised learning is learning without computers problem based learning learning from environment learning from teachers
ans: learning from environment
52. Perceptron is General class of approaches to a problem. Performing several computations simultaneously Structures in a database those are statistically relevant Simple forerunner of modern neural networks, without hidden layers.
ans: Simple forerunner of modern neural
networks, without hidden layers.
53. In supervised learning classes are not predefined classes are predefined classes are not required classification is not done
ans: classes are predefined
54. What is composed of large number of highly interconnected processing elements (neurons) working in unison to solve problems. ANN Perceptron neuron None of these
ans: ANN
55. Artificial neural network used for Pattern Recognition Classification Clustering All of these
ans: All of these
56. A Neural Network can answer For Loop questions what-if questions IF-Then-Else Analysis Questions None of these
ans: what-if questions
57. Ability to learn how to do tasks based on the data given for training or initial experience Self-Organization Adaptive Learning Fault tolerance Robustness
ans: Adaptive Learning
58. When the cell is said to be fired if potential of body reaches a steady threshold values if there is impulse reaction during upbeat of heart None of these
ans: if potential of body reaches a
steady threshold values
59. In artificial Neural Network interconnected processing elements are called nodes or neurons weights axons Soma
ans: nodes or neurons
60. Each connection link in ANN is associated with ________ which has information about the input signal. neurons weights bias activation function
ans: weights
61. What was the 2nd stage in perceptron model called? sensory units summing unit association unit output unit
ans: association unit
62. which is called Internal state of neuron that is the function of the inputs the neurons receives Weight activation or activity level of neuron Bias None of these
ans: activation or activity level of neuron
63. How many signal(s) can Neuron send at a time? multiple 1 2 None of these
ans: 1
64. Artificial neural network is based on the concept gradient descent technique random descent technique biological neuron (a) and (c).
ans: (a) and (c)
65. Kohonen network / adaptive resonance theory model is purely unsupervised supervised reinforcement none of these.
ans: purely unsupervised
66. Classification of XOR input pattern is separable by perceptron model separable by Kohonen model separable by multilayer feedback network all of these.
ans: separable by perceptron model
67. In ANN model learning constant should be small should be constant throughout the epoch should be ‘one’ Should be small but adaptive and remain stable to irrelevant input.
ans: Should be small but adaptive and
remain stable to irrelevant input.
68. Acquired knowledge is stored in the ANN with the help of activation function local induced field synaptic weight input signal.
ans: synaptic weight
69. Expert systems Combining different types of method or information Approach to the design of learning algorithms that is structured along the lines of the theory of evolution an information base filled with the knowledge of an expert formulated in terms of if-then rules None of these
ans: an information base filled with
the knowledge of an expert
formulated in terms of if-then
rules
70. Falsification is Modular design of a software application that facilitates the integration of new modules Showing a universal law or rule to be invalid by providing a counter example A set of attributes in a database table that refers to data in another table None of these
ans: Showing a universal law or rule to be
invalid by providing a counter example
71. Evolutionary computation is Combining different types of method or information Approach to the design of learning algorithms that is structured along the lines of the theory of evolution. Decision support systems that contain an information base filled with the knowledge of an expert formulated in terms of if-then rules. None of these
ans:Approach to the design of learning
algorithms that is structured along the
lines of the theory of evolution.
72. Extendible architecture is Modular design of a software application that facilitates the integration of new modules
Showing a universal law or rule to be invalid by providing a counter example A set of attributes in a database table that refers to data in another table None of these
ans: Modular design of a software application that facilitates the integration of new modules
73. Massively parallel machine is A programming language based on logic A computer where each processor has its own operating system, its own memory, and its own hard disk Describes the structure of the contents of a database. None of these
ans: A computer where each processor has
its own operating system, its own
memory, and its own hard disk
74. Search space The large set of candidate solutions possible for a problem The information stored in a database that can be retrieved with a single query. Worth of the output of a machine learning program that makes it understandable for humans None of these
ans: The large set of candidate
solutions possible for a problem
75. Shallow knowledge The large set of candidate solutions possible for a problem The information stored in a database that can be retrieved with a single query Worth of the output of a machine learning program that makes it understandable for humans All of these
ans: The information stored in a database
that can be retrieved with a single query
76. Quantitative attributes are A reference to the speed of an algorithm, which is quadratically dependent on the size of the data Attributes of a database table that can take only numerical values Tools designed to query a database All of these
ans: Attributes of a database table that can
take only numerical values
77. Subject orientation The science of collecting, organizing, and applying numerical facts Measure of the probability that a certain hypothesis is incorrect given certain observations. One of the defining aspects of a data warehouse, which is specially built around all the existing applications of the operational data None of these
ans: One of the defining aspects of a
data warehouse, which is
specially built around all the
existing applications of the
operational data
78. Vector It does not need the control of the human operator during their execution An arrow in a multi-dimensional space. It is a quantity usually characterized by an ordered set of scalars The validation of a theory on the basis of a finite number of examples All of these
ans: An arrow in a multi-dimensional space.
It is a quantity usually characterized by
an ordered set of scalars
79. Transparency The large set of candidate solutions possible for a problem The information stored in a database that can be retrieved with a single query Worth of the output of a machine learning program that makes it understandable for humans None of these
ans: Worth of the output of a
machine learning program that
makes it understandable for
humans
80. An auto-associative network is a neural network that contains no loops a neural network that contains feedback a neural network that has only one loop a single layer feed-forward neural network with pre-processing
ans: a neural network that contains feedback
81. Which of the following is true? (i) On average, neural networks have higher computational rates than conventional computers. (ii) Neural networks learn by example. (iii) Neural networks mimic the way the human brain works. All of these ii and iii i, ii and iii None of these
ans: All of these
82. Which of the following is true for neural networks? (i) The training time depends on the size of the network. (ii) Neural networks can be simulated on a conventional computer. (iii) Artificial neurons are identical in operation to biological ones. All of these ii and iii i and ii None of these
ans: i and ii
83. What are the advantages of neural networks over conventional computers? (i) They have the ability to learn by example (ii) They are more fault tolerant (iii) They are more suited for real time operation due to their high ‘computational’ rates All of these ii and iii i, ii None of these
ans: All of these
84 Which of the following is true? Single layer associative neural networks do not have the ability to: (i) perform pattern recognition (ii) find the parity of a picture (iii)determine whether two or more shapes in a picture are connected or not All of these ii and iii i, ii None of these
ans: ii and iii
85 Factors which affect the performance of learner system does not include Representation scheme used Training scenario Type of feedback Good data structures
ans: Good data structures
86 Different learning methods does not include Memorization Analogy Deduction Introduction
ans: Introduction
87 In language understanding, the levels of knowledge that does not include Phonological Syntactic Empirical Logical
ans: Empirical
88 A model of language consists of the categories which does not include Language units Role structure of units System constraints Structural units
ans: Structural units
89 What is a top-down parser? Begins by hypothesizing a sentence (the symbol S) and successively predicting lower level constituents until individual preterminal symbols are written Begins by hypothesizing a sentence (the symbol S) and successively predicting upper level constituents until individual preterminal symbols are written Begins by hypothesizing lower level constituents and successively predicting a sentence (the symbol S) Begins by hypothesizing upper level constituents and successively predicting a sentence (the symbol S)
ans: Begins by hypothesizing a
sentence (the symbol S) and
successively predicting lower
level constituents until
individual preterminal symbols
are written
90 Among the following which is not a horn clause? p Øp V q p → q p → Øq
ans: p → Øq
91 Which instruments are used for perceiving and acting upon the environment? Sensors and Actuators Sensors Perceiver None of these
ans: Sensors and Actuators
92 What is meant by agent’s percept sequence? Used to perceive the environment Complete history of actuator Complete history of perceived things None of these
ans: Complete history of perceived things
93 Single layer perceptron is used for linear seperability error minimization non-linear separability annealing.
ans: linear seperability
94 Which mode of training, all neurons in Hopfield networks fire at random. Stable status Output Synchronous Asynchronous
ans: Synchronous
95 X-OR problem can be solved by single layer perceptron Bayes theorem multi-layer perceptron single layer perception and Bayes theorem
ans: single layer perception and Bayes theorem
96 For a network with inputs [ x1, x2, x3 ]= [ 0 3,0.5,0.6] and weights [w1,w2 ,w3 ] = [ 0 2, 0 1, -0 3] , the net output to the output M-P neuron is 0·07 – 0·07 0·7 – 0·7.
ans: – 0·07
97 In fuzzy logic controller the rule base is updated by the help of Fuzzy logic ANN and GA Hebb's rule none of these.
ans: ANN and GA
98 If a problem is linearly separable, then we can find the weight vector Wi, such that Wi T . X > 0 for each X, with desired output '+1' and Wi T . X < 0 , for each X, with desired output '–1'. True False Can't say None of these.
ans: True
99 For a 3-input neuron representing a perceptron, where [x1 ,x2 ,x3 ] = [ 0 8, 0 6, 0 4 ] and weights [ w1,w2 ,w3 ]= [ 0 1, 0 3, 0 2 ] and bias b = 0·35, the output of the neuron using bipolar sigmoid activation function is 0·625 0·764 0·259 0·346.
ans: 0·346
100 Which one is unsupervised learning rule? Error-correction Delta Widrow-Hoff Hebbian.
ans: Hebbian
101 In simple perceptron learning rule change of synaptic weight is proportional to product of error and i/p signal product of i/p and o/p signals product of error and o/p signal Gradient of cost function.
ans: product of i/p and o/p signals
102 Which is the most direct application of neural networks? vector quantization pattern mapping pattern classification control applications
ans: pattern classification
103 What are pros of neural networks over computers? they have ability to learn b examples they have real time high computational rates they have more tolerance All of these
ans: All of these
104 What is the rule of simple reflex agent Simple-action rule Condition-action rule Simple & Condition-action rule None of these
ans: Condition-action rule
105 Neuro software is: A software used to analyze neurons It is powerful and easy neural network Designed to aid experts in real world It is software used by Neurosurgeon
ans: It is powerful and easy neural network
106 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: 000 or
110 or 011 or 101 010 or 100 or 110 or 101 000 or 010 or 110 or 100 100 or 111 or 101 or 001
ans: 000 or 010 or 110 or 100
107 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: 238 76 119 123
ans: 238
108 What happens in upper subnet of the hamming network? classification storage output None of these
ans: None of these
109 The competition in upper subnet of hamming network continues till? only one unit remains negative all units are destroyed output of only one unit remains positive None of these
ans: output of only one unit remains positive
110 Which is true for neural networks? It has set of nodes and connections Each node computes it’s weighted input Node could be in excited state or non-excited state All of these
ans: All of these
111 What is shape of dendrites like oval round tree rectangular
ans: tree
112 What are the issues on which biological networks proves to be superior than AI networks? robustness & fault tolerance flexibility collective computation All of these
ans: All of these
113 What are dendrites? fibers of nerves nuclear projections other name for nucleus None of these
ans: fibers of nerves
114 Feature of ANN in which ANN creates its own organization or representation of information it receives during learning time is Adaptive Learning Self-Organization What-If Analysis Supervised Learning
ans: Self-Organization
115 Signal transmission at synapse is a? physical process chemical process physical & chemical both None of these
ans: chemical process
116 What is purpose of Axon? receptors transmitter transmission None of these
ans: transmission
117 What is approx size of neuron body(in micrometer) below 5 5-10 10-80 above 100
ans: 10-80
118 Where does the chemical reaction take place in neuron? dendrites axon synapses nucleus
ans: synapses
119 Function of dendrites is? Receptors transmitter both receptor & transmitter None of these
ans: Receptors
120 Prolog is A programming language based on logic A computer where each processor has its own operating system, its own memory, and its own hard disk Describes the structure of the contents of a database None of these
ans: A programming language based on logic
121 Back propagation is a learning technique that adjusts weights in the neural network by propagating weight changes. Forward from source to sink Backward from sink to source Forward from source to hidden nodes Backward from sink to hidden node
ans: Backward from sink to source
122 What is the gap at synapses(in nanometer) 50 100 150 200
ans: 200
123 An artificial neuron receives n inputs x1, x2, x3............xn with weights w1, w2, ..........wn attached to the input links. The weighted sum_________________ is computed to be passed on to a non-linear filter Φ called activation function to release the output. Σ wi Σ xi Σ wi* xi None of these
ans: Σ wi* xi
124 How does the transmission/pulse acknowledged by lowering electric potential of neuron body by raising electric potential of neuron body both by lowering & raising electric potential None of these
ans: both by lowering & raising electric potential
125 Slots and facets are used in Semantic Networks Frames Rules All of these
ans: Frames
126 A neuron with 3 inputs has the weight vector [0.2 -0.1 0.1] and a bias θ = 0. If the input vector is X = [0.2 0.4 0.2] then the total input to the neuron is: 0.20 1.0 0.02 -1.0
ans: 0.02
127. Which of the following neural networks uses supervised learning? (A) Multilayer perceptron (B) Self organizing feature map (C) Hopfield network (A) only (B) only (A) and (B) only (A) and (C) only
ans: (A) only
128. What is charge at protoplasm in state of inactivity positive negative neutral may be positive or negative
ans: negative
129. What is the main constituent of neural liquid? sodium potassium Iron None of these
ans: sodium
130. What is average potential of neural liquid in inactive state +70mv +35mv -35mv -70mv
ans: -70mv
131. What is effect on neuron as a whole when its potential get raised to -60mv it get fired no effect it get compressed it expands
ans: it get fired
132. What is the function of neurotransmitter? they transmit data directly at synapse to other neuron they modify conductance of post synaptic membrane for certain ions cause polarization or depolarization both polarization & modify conductance of membrane
ans: both polarization & modify conductance
of membrane
133. The cell body of neuron can be analogous to what mathematical operation? Summing Differentiator integrator None of these
ans: Summing
134. What is the critical threshold voltage values at which neuron get fired? 30mv 20mv 25mv 10mv
ans: 10mv
135. Why can’t we design a perfect neural network? full operation is still not known of biological neurons number of neuron is itself not precisely known number of interconnection is very large & is very complex All of these
ans: All of these
136. How many synaptic connections are there in human brain?
10^10 10^15 10^20 10^5
ans: 10^15
137. Operations in the neural networks can perform what kind of operations? serial parallel serial or parallel None of these
ans: serial or parallel
138. Which action is faster pattern classification or adjustment of weights in neural nets? pattern classification adjustment of weights equal either of them can be fast, depending on conditions
ans: pattern classification
139. What is the feature of ANNs due to which they can deal with noisy, fuzzy, inconsistent data? associative nature of networks distributive nature of networks both associative & distributive None of these
ans: both associative & distributive
140. What was the name of the first model which can perform weighted sum of inputs? McCulloch-pitts neuron model Marvin Minsky neuron model Hopfield model of neuron None of these
ans: McCulloch-pitts neuron model
141. Who developed the first learning machine in which connection strengths could be adapted automatically? McCulloch-pitts Marvin Minsky Hopfield None of these
ans: Marvin Minsky
142. Who proposed the first perceptron model in 1958? McCulloch-pitts Marvin Minsky Hopfield Rosenblatt
ans: Rosenblatt
143. John Hopfield was credited for what important aspect of neuron? learning algorithms adaptive signal processing energy analysis None of these
ans: energy analysis
144. What is the contribution of Ackley, Hinton in neural? Perceptron Boltzmann machine learning algorithms None of these
ans: Boltzmann machine
145. What is ART in neural networks automatic resonance theory artificial resonance theory adaptive resonance theory None of these
ans: adaptive resonance theory
146. What is an activation value? weighted sum of inputs threshold value main input to neuron None of these
ans: weighted sum of inputs
147. Positive sign of weight indicates? excitatory input inhibitory input can be either excitatory or inhibitory as such None of these
ans: excitatory input
148. Negative sign of weight indicates? excitatory input inhibitory input excitatory output inhibitory output
ans: inhibitory input
149. The amount of output of one unit received by another unit depends on what? output unit input unit activation value weight
ans: weight
150. The process of adjusting the weight is known as? activation synchronization learning None of these
ans: learning
151. The procedure to incrementally update each of weights in neural is referred to as? synchronisation learning law learning algorithm both learning algorithm & law
ans: both learning algorithm & law
152. In what ways can output be determined from activation value? deterministically stochastically both deterministically & stochastically None of these
ans: both deterministically & stochastically
153. How can output be updated in neural network? synchronously asynchronously both synchronously & asynchronously None of these
ans: both synchronously & asynchronously
154. What is asynchronous update in neural networks? output units are updated sequentially output units are updated in parallel fashion can be either sequentially or in parallel fashion None of these Unit IV
ans: output units are updated sequentially
155. In GA term ‘Gene’ is termed as coded design vector coded design variable every bit None of these.
ans: coded design vector
156. A particular set of genes in genome is called alleles chromosome locus Genotype.
ans: chromosome
157. Which search strategy is also called as blind search? Uninformed search Informed search Simple reflex search All of these
ans: Uninformed search
158. How many types are available in uninformed search method? 3 4 5 6
ans: 5
159. Which search is implemented with an empty first-in-first-out queue? Depth-first search Breadth-first search Bidirectional search None of these
ans: Breadth-first search
160. When breadth-first search is optimal? When there is less number of When all step costs are equal nodes When all step costs are unequal None of these
ans: When all step costs are equal
161. How many successors are generated in backtracking search?
1 2 3 4
ans: 1
162. Which algorithm is used to solve any kind of problem? Breadth-first algorithm Tree algorithm Bidirectional search algorithm None of these
ans: Tree algorithm
163. Which search algorithm imposes a fixed depth limit on nodes? Depth-limited search Depth-first search Iterative deepening search Bidirectional search
ans: Depth-limited search
164. Which search implements stack operation for searching the states? Depth-limited search Depth-first search Iterative deepening search Bidirectional search
ans: Depth-first search
165. What is the space complexity of Depth-first search O(b) O(bl) O(m) O(bm)
ans: O(bm)
166. Strategies that know whether one non-goal state is “more promising” than another are called Informed Search Uninformed Search Informed & Uninformed Search Informed and Heuristic Search
ans: Informed and Heuristic Search
167. Which of the following is/are Uninformed Search technique/techniques Breadth First Search (BFS) Depth First Search (DFS) Bidirectional Search All of these
ans: All of these
168. What is the complexity of minimax algorithm? Same as of DFS Space – bm and time – bm Time – bm and space – bm Same as BFS
ans: Same as of DFS
169. The size of each chromosome for the problem maximizing a function f ( x ) = x2 in the interval 0 ≤ x ≤ 3 1 is 8 5 4 None of these.
ans: 4
170. Adversarial search problems uses Competitive Environment Cooperative Environment Neither Competitive nor Cooperative Environment None of these
ans: Competitive Environment
171. Zero sum game has to be a ______ game. Single player Two player Multiplayer All of these
ans: Multiplayer
172. A game can be formally defined as a kind of search problem with the following components Initial State Successor Function Terminal Test All of these
ans: All of these
173. General algorithm applied on game tree for making decision of win/lose is ____________ DFS/BFS Search Algorithms Heuristic Search Algorithms Greedy Search Algorithms MIN/MAX Algorithms
ans: MIN/MAX Algorithms
174. Which of the following is/are found in Genetic Algorithms? I. Evolution II. Selection III. Reproduction IV. Mutation (I) & (II) (I), (II) & (III) (II), (III) & (IV) All of these.
ans: All of these.
175. Genetic Algorithm are a part of Evolutionary Computing inspired by Darwin's theory about evolution - "survival of the fittest" are adaptive heuristic search algorithm based on the evolutionary ideas of natural All of these selection and genetics
ans: All of these
176 The time and space complexity of BFS is (For time and space complexity problems consider b as branching factor and d as depth of the search tree.) O(bd+1) and O(bd+1) O(b2) and O(d2) O(d2) and O(b2) O(d2) and O(d2)
ans: O(bd+1) and O(bd+1)
177. uniform-cost search expands the node n with the __________ Lowest path cost Heuristic cost Highest path cost Average path cost
ans: Lowest path cost
178. Which is not optimal when all step costs are equal, because it always expands the shallowest unexpanded node? Breadth-first search Depth First Search (DFS) Bidirectional Search All of these
ans: Breadth-first search
179. Depth-first search always expands the ______ node in the current fringe of the search tree. Shallowest Child node Deepest Minimum cost
ans: Deepest
180. Breadth-first search always expands the ______ node in the current fringe of the search tree. Shallowest Child node Deepest Minimum cost
ans: Shallowest
181. Optimality of BFS is ___________ When there is less number of nodes When all step costs are equal When all step costs are unequal None of these
ans: When all step costs are equal
182. LIFO is ______ where as FIFO is ________ Stack, Queue Queue, Stack Priority Queue, Stack Stack. Priority Queue
ans: Stack, Queue
183. When the environment of an agent is partially observable in search space following problem/problems could occur. Sensorless problems: If the agent has no sensors at all, then (as far as it knows) it could be in one of several possible initial states, and each action might therefore lead to one of several possible successor states Contingency problems: If the environment is partially observable or if actions are uncertain, then the agent’s percepts provide new information after each action. Each possible percept defines a contingency that must be planned for. A problem is called adversarial if the uncertainty is caused by the actions of another agent Exploration problems: When the states and actions of the environment are unknown, the agent must act to discover them. Exploration problems can be viewed as an extreme case of contingency problems
All of these
ans: All of these
184. For general graph, how one can get rid of repeated states? By maintaining a list of visited vertices By maintaining a list of traversed edges By maintaining a list of nonvisited vertices By maintaining a list of non-traversed edges
ans: By maintaining a list of visited vertices
185. DFS is ______ efficient and BFS is __________ efficient Space, Time Time, Space Time, Time Space, Space
ans: Space, Time
186. The main idea of _______is to reduce the time complexity by searching two ways simultaneously from start node and another from goal node. Bidirectional search DFS BFS All of these
ans: Bidirectional search
187. What is the other name of informed search strategy Simple search Heuristic search Online search None of these
ans: Heuristic search
188. How many types of informed search method are in artificial intelligence?
1 2 3 4
ans: 4
189. Which search uses the problem specific knowledge beyond the definition of the problem? Informed search Depth-first search Breadth-first search Uninformed search
ans: Informed search
190. Which function will select the lowest expansion node at first for evaluation? Greedy best-first search Best-first search Depth-first searc None of these
ans: Best-first search
191. What is the heuristic function of greedy best-first search? f(n) != h(n) f(n) < h(n) f(n) = h(n) f(n) > h(n)
ans: f(n) = h(n)
192. Which search uses only the linear space for searching? Best-first search Recursive best-first search Depth-first search None of these
ans: Recursive best-first search
193. Which method is used to search better by learning? Best-first search Depth-first search Metalevel state space None of these
ans: Metalevel state space
194. Which is used to improve the performance of heuristic search? Quality of nodes Quality of heuristic function Simple form of nodes None of these
ans: Quality of heuristic function
195. A heuristic is a way of trying ___________ To discover something or an idea embedded in a program To search and measure how far a node in a search tree seems to be from a goal To compare two nodes in a search tree to see if one is better than another All of these
ans: All of these
196 Best-First search is a type of informed search, which uses ________________ to choose the best next node for expansion. Evaluation function returning lowest evaluation Evaluation function returning highest evaluation Evaluation function returning lowest & highest evaluation None of them is applicable
ans: Evaluation function returning lowest evaluation
197. Best-First search can be implemented using the following data structure. Queue Stack Priority Queue Circular Queue
ans: Priority Queue
198. Heuristic function h(n) is ________ Lowest path cost Cheapest path from root to goal node
Estimated cost of cheapest path from root to goal node Average path cost
ans: Estimated cost of cheapest path from root to goal node
199. “Fittest will be survivor” is true for Reinforcement learning Tabu search Genetic Algorithm ACO
ans:Genetic Algorithm
200. Random descent is true for Simulated annealing ACO Genetic Algorithm Tabu search
ans:Simulated annealing
Comments
Post a Comment