0% found this document useful (0 votes)
451 views40 pages

Hide Answer Workspace

The document contains 23 multiple choice questions about fuzzy logic, neural networks, and related concepts. Some key points covered include: - Fuzzy logic is associated with many-valued logic rather than crisp/two-valued logic. It allows for partial set membership between 0 and 1. - Neural networks learn from examples, can operate in parallel for high computational rates, and are fault tolerant. Backpropagation allows weights to be adjusted so the network can learn by transmitting error back through the network. - Perceptrons are single layer feedforward neural networks that can partition linear parts of space to solve problems like XOR that single perceptrons cannot handle alone. However, perceptrons cannot inherently learn complex nonlinear functions.

Uploaded by

Nikhil Tiwari
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
451 views40 pages

Hide Answer Workspace

The document contains 23 multiple choice questions about fuzzy logic, neural networks, and related concepts. Some key points covered include: - Fuzzy logic is associated with many-valued logic rather than crisp/two-valued logic. It allows for partial set membership between 0 and 1. - Neural networks learn from examples, can operate in parallel for high computational rates, and are fault tolerant. Backpropagation allows weights to be adjusted so the network can learn by transmitting error back through the network. - Perceptrons are single layer feedforward neural networks that can partition linear parts of space to solve problems like XOR that single perceptrons cannot handle alone. However, perceptrons cannot inherently learn complex nonlinear functions.

Uploaded by

Nikhil Tiwari
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 40

1) Which of the following is associated with fuzzy logic?

a. Crisp set logic

b. Many-valued logic

c. Two-valued logic

d. Binary set logic

Hide Answer Workspace

Answer: b) Many-valued logic

Explanation: Since fuzzy logic can define the set membership with some specific
value, it may have multiple set values.

2) 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.

c. Either 0 or 1, between 0 & 1.

d. Between 0 & 1, between 0 & 1.

Hide Answer Workspace

Answer: c) Either 0 or 1, between 0 & 1.

Explanation: A crisp set is usually defined by crisp boundaries containing the precise
location of the set boundaries.

However, a fuzzy set is defined by the indeterminate boundaries containing uncertainty


about the set's boundaries.

3) A Fuzzy logic is an extension to the Crisp set, which handles the Partial
Truth.

a. True

b. False
Hide Answer Workspace

Answer: a) True.

Explanation: None.

4) How many types of random variables are there in Fuzzy logic?

a. 2

b. 4

c. 1

d. 3

Hide Answer Workspace

Answer: d) 3

Explanation: There are three types of random variables, i.e., Boolean, discrete, and
continuous variables.

5) Which of the following represents the values of set membership?

a. Degree of truth

b. Probabilities

c. Discrete set

d. Both a & b

Hide Answer Workspace

Answer: b) Degree of truth

Explanation: Both probabilities and degree of truth range between 0 and 1.

6) The probability density function is represented by

a. Continuous variable
b. Discrete variable

c. Probability distributions for Continuous variables

d. Probability distributions

Hide Answer Workspace

Answer: c) Probability distributions for Continuous variables

Explanation: None.

7) _________is used for probability theory sentences.

a. Logic

b. Extension of propositional logic

c. Conditional logic

d. None of the above

Hide Answer Workspace

Answer: b) Extension of propositional logic

Explanation: The version of probability theory makes use of an extension of


propositional logic for its sentences.

8) Which of the following fuzzy operators are utilized in fuzzy set theory?

a. AND

b. OR

c. NOT

d. EX-OR

Hide Answer Workspace

Answer: a), b) and c)

Explanation: In fuzzy logic, the AND, OR, and NOT operators represent the minimum,
maximum, and complement.
9) What is the name of the operator in fuzzy set theory, which is found to be
linguistic in nature?

a. Lingual Variable

b. Fuzz Variable

c. Hedges

d. None of the above

Hide Answer Workspace

Answer: c) Hedges

Explanation: None.

10) Where can we use the Bayes rule?

a. To increase the complexity.

b. To decrease the complexity.

c. To solve queries

d. To answer the probabilistic query

Hide Answer Workspace

Answer: d) To answer the probabilistic query

Explanation: Based on the given evidence, the Bayes rule can be utilized to answer
the probabilistic queries.

11) Which of the following is offered by the Bayesian network?

a. Partial description of the domain

b. A complete description of the domain

c. A complete description of the problem

d. None of the above


Hide Answer Workspace

Answer: b) Complete description of the domain

Explanation: A Bayesian network refers to a probabilistic graphical model, which


epitomizes a set of variables and its corresponding dependencies thru a directed acyclic
graph (DAG).

12) _________ represents the fuzzy logic

a. IF-THEN rules

b. IF-THEN-ELSE rules

c. Both a & b

d. None of the above

Hide Answer Workspace

Answer: a) IF-THEN rules

Explanation: In fuzzy set theory, the fuzzy operators are defined on the fuzzy sets.
When the fuzzy operators are anonymous, the fuzzy logic utilizes the IF-THEN rules.

In general, rules are expressed as:

IF variable IS property THEN action

13) Uncertainty can be represented by _________

a. Entropy

b. Fuzzy logic

c. Probability

d. All of the above

Hide Answer Workspace

Answer: d) All of the above

Explanation: Entropy is the amount of uncertainty involved in data, which is


represented by H(data).
14) Name the algorithms that acquire from complex environments to
generalize, approximate and simplify solution logic.

a. Ecorithms

b. Fuzzy set

c. Fuzzy Relational DB

d. None of the above

Hide Answer Workspace

Answer: b) Fuzzy set

Explanation: Rather than being associated with exponential growth, local structures
are generally linked with linear growth in terms of complexity.

15) Which of the following condition can directly influence a variable by all the
others?

a. Fully connected

b. Local connected

c. Partially connected

d. None of the above

Hide Answer Workspace

Answer: a) Fully Connected

Explanation: None.

16) 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

Hide Answer Workspace

Answer: d) A single layer feed-forward neural network with pre-processing

Explanation: A perceptron is a single-layer neural network that consists of input


values, weights, bias, net sum followed by an activation function.

17) What is meant by an auto-associative neural network?

a. A neural network including feedback

b. A neural network containing no loops

c. A neural network having a single loop

d. A single layer feed-forward neural network containing feedback

Hide Answer Workspace

Answer: a) A neural network including feedback

Explanation: Auto associative networks are yet another kind of feed-forward nets
trained to estimate the identity matrix in between network inputs and outputs by
incorporating backpropagation.

18) Which of the following is correct?

I. In contrast to conventional computers, neural networks have much higher


computational rates.

II. Neural networks learn by example.

III. Neural networks mimic the same way as that of the human brain

a. All of the above

b. (ii) and (iii) are true

c. (i), (ii) and (iii) are true

d. None of the above


Hide Answer Workspace

Answer: a) All of the above

Explanation: Neural networks can run multiple operations in parallel, which is why
they have higher computational rates than conventional computers. Neural nets mimic
the working of the human brain. The idea behind neural nets is not to be programmed
but to learn by examples.

19) Which of the following is correct for the neural network?

I. The training time is dependent on the size of the network

II. Neural networks can be simulated on the conventional computers

III. Artificial neurons are identical in operation to a biological one

a. All of the above

b. (ii) is true

c. (i) and (ii) are true

d. None of the above

Hide Answer Workspace

Answer: c) (i) and (ii) are true

Explanation: The training time depends on the network size; the more the number of
neurons, the more would be the possible states. Neural networks can be simulated on a
conventional computer, but neural networks' main advantage - parallel execution - is
lost. Artificial neurons are not identical in operation to biological ones.

20) What are the advantages of neural networks over conventional computers?

I. Neural networks learn from examples

II. They are more fault-tolerant

III. They are well suited for real-time operation due to their high computational rates

a. (i) and (ii) are correct


b. (i) and (iii) are correct

c. Only (i)

d. All of the above

Hide Answer Workspace

Answer: d) All of the above

Explanation: Since neural networks learn by example, they are more fault-tolerant
than conventional computers because they always respond, and small changes in the
input do not hamper the output. Neural networks encompass parallel architecture, so it
is pretty easy to achieve high computational rates.

21) 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

Hide Answer Workspace

Answer: c) It is the transmission of error back through the network to allow weights to
be adjusted so that the network can learn.

Explanation: Backpropagation is an efficient approach used to compute loss function's


stress with respect to the parameters of neural networks. In order to minimize the loss
function, backpropagation is mainly used to tune the weights of deep neural networks.

22) 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


Hide Answer Workspace

Answer: c) It can explain the result

Explanation: The artificial neural networks fail to explain the results.

23) Having multiple perceptrons can solve the XOR problem satisfactorily
because each perceptron can partition off a linear part of the space itself, and
they can then combine their results.

a. True - This works always, and these multiple perceptrons learn to classify even
complex problems.

b. False - Perceptrons are mathematically incapable of solving linearly inseparable


functions, no matter what you do

c. True - Perceptron can do this but are unable to learn to do it - they have to be
explicitly hand-coded

d. False - Just having a single perceptron is enough

Hide Answer Workspace

Answer: c) True - Perceptron can do this but are unable to learn to do it - they have to
be explicitly hand-coded

Explanation: None

24) Based on _________ membership function can be used to solve empirical


problems.

a. Knowledge

b. Learning

c. Examples

d. Experience

Hide Answer Workspace

Answer: d) Experience
Explanation: The membership function of a fuzzy set is a generalization of the
indicator function for classical sets.

25) A 3-input neuron is trained to output a 0 when the input is 110 and a 1
when the input is 111. After generalization, the output will be 0, when and only
when the input is:

a. 000 or 110 or 011 or 101

b. 000 or 010 or 110 or 100

c. 100 or 111 or 101 or 001

d. 010 or 100 or 110 or 101

Show Answer Workspace

26) 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. 76

b. 238

c. 123

d. 119

Hide Answer Workspace

Answer: b) 238

Explanation: In order to find out the output, we multiply the weights with their
respective inputs, add the results and then further multiply them with their transfer
function.

Thus, output= 2*(1*4 + 2*10 + 3*5 + 4*20) = 238

27) A neuro software can be defined as:

a. A powerful and easy neural network

b. A software that is used to analyze neurons


c. Software utilized by a neurosurgeon

d. A software aimed to assist experts in the real world

Hide Answer Workspace

Answer: a) A powerful and easy neural network

Explanation: None.

28) 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

Hide Answer Workspace

Answer: d) Recurrent Neural Network

Explanation: A recurrent neural network is yet another kind of artificial neural


network, where the output derived from the previous step is fed as an input to the
current step.

29) 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

e. Neither inputs nor outputs are given

Hide Answer Workspace

Answer: b) Some specific output values aren't disclosed


Explanation:

In unsupervised learning, the model learns itself from the data without having a
predicted result. Either the data is not given with a target response variable (label), or
none chooses to label a response. In general, it is mainly treated as a pre-processing
step for supervised learning models.

Here, the goal is to determine the patterns, deep insights, understand variation, find
unknown subgroups (amongst the variables or observations), and so on in the data.

30) What is involved in inductive learning?

a. Inconsistent Hypothesis

b. Consistent Hypothesis

c. Estimated Hypothesis

d. Irregular Hypothesis

e. Regular Hypothesis

Hide Answer Workspace

Answer: b) Consistent Hypothesis

Explanation: Inductive learning is used to find a consistent hypothesis, which agrees


with the examples. The difficulty of the task relies on the chosen representation.

31) Which of the following statement is correct?

a. Not all formal languages are context-free

b. All formal languages are context-free

c. All formal languages are like natural language

d. Natural languages are context-oriented free

e. Natural language is normal

Hide Answer Workspace

Answer: a) Not all formal languages are context-free

Explanation: Not all formal languages are context-free.


32) Which of the following is incorrect?

a. The union and intersection of two context-free languages are context-free.

b. The reverse of context-free language is context-free, but its complement does


not need to be.

c. Every regular language is context-free as it can be easily explained by regular


grammar.

d. The intersection of a context-free language and a regular language is always


context-free.

e. The intersection of two context-free languages is context-free.

Hide Answer Workspace

Answer: e) The intersection of two context-free languages is context-free.

Explanation: The union and concatenation of two context-free languages are always
context-free, but the intersection need not be context-free.

33) Automated vehicle is an application of _________

a. Unsupervised learning

b. Supervised learning

c. Reinforcement learning

d. Active learning

Hide Answer Workspace

Answer: b) Supervised learning

Explanation: In an automatic vehicle, a set of input visions and corresponding actions


are available for learners, so it can be concluded that it is an example of supervised
learning.

34) _________ is not counted in different learning method.


a. Analogy

b. Memorization

c. Introduction

d. Deduction

Hide Answer Workspace

Answer: c) Introduction

Explanation: Analogy, memorization, and deduction are involved in different learning


methods.

35) 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

Hide Answer Workspace

Answer: d) All of the above

Explanation: Neural networks, Decision trees, Propositional and FOL rules are
altogether utilized as a learning model.

36) Which of the following is the correct example of active learning?

a. Dust Cleaning Machine

b. News Recommender System

c. Automated Vehicle

d. None of the above

Hide Answer Workspace

Answer: b) News Recommender System


Explanation: Active learning is such a kind of learning, which involves the teachers. It
enables the learner to ask relevant examples related to perception-action pairs that will
further augment the performance.

37) Which of the following is termed exploratory learning?

a. Active learning

b. Supervised learning

c. Reinforcement learning

d. Unsupervised learning

Hide Answer Workspace

Answer: d) Unsupervised learning

Explanation: Exploratory learning can be defined as a teaching and learning approach


that encourages the learner to study and scrutinize new material, regardless of being
dependent on any supervision.

38) _________ helps in modifying the performance element, assisting in


making a better decision.

a. Learning element

b. Performance element

c. Changing element

d. None of the above

Hide Answer Workspace

Answer: a) Learning element

Explanation: Learning elements assist in making a better decision by modifying the


performance element.

39) Which of the following is considered while determining the nature of the
learning problem?
a. Problem

b. Feedback

c. Environment

d. All of the above

Hide Answer Workspace

Answer: b) Feedback

Explanation: The feedback is utilized to determine the nature of the learning problem
faced by the agent.

40) Which of the following is chosen among the multiple consistent hypotheses?

a. Ockham razor

b. Learning element

c. Razor

d. None of the above

Hide Answer Workspace

Answer: a) Ockham razor

Explanation: Ockham razor prefers the simplest hypothesis consistent with the data
intuitively.

41) Which of the following takes input as an object described by a set of


attributes?

a. Graph

b. Decision graph

c. Tree

d. Decision tree

Hide Answer Workspace


Answer: d) Decision tree

Explanation: The decision tree takes input as an object described by a set of attributes
followed by returning a decision.

42) A neural network can answer

a. For Loop questions

b. What-if questions

c. If-The-Else Analysis questions

d. None of the above

Hide Answer Workspace

Answer: b) What-if questions

Explanation: None

43) 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

Hide Answer Workspace

Answer: c) Self-Organization

Explanation: The term self-organization refers to how people unify their common
behavior to form global order by interacting among themselves instead of interacting
through external intervention and instruction.

44) In artificial neural network, interconnected processing elements are termed


as _________
a. Weights

b. Nodes or neurons

c. Axon

d. Soma

Hide Answer Workspace

Answer: b) Nodes or neurons

Explanation: A neural network comprises several simple, highly interconnected


processing elements that process data by its dynamic state response to external
elements.

45) Each connection link in ANN is linked with ________ that contains statics
about the input signal.

a. Neurons

b. Activation function

c. Weights

d. Bias

Hide Answer Workspace

Answer: c) Weights

Explanation: Weights in artificial neural networks play an efficient role as they are
responsible for transmuting the input data within the network's hidden layers.

46) Artificial neurons are capable enough to model original neurons networks
similarly as they are found in the human brain

a. True

b. False

Hide Answer Workspace

Answer: a) True
Explanation: None.

47) Name the input function received by neurons, which is also known as the
neuron's internal state.

a. Weight

b. Bias

c. Activation or neuron's activity level

d. None of the above

Hide Answer Workspace

Answer: c) Activation or neuron's activity level

Explanation: None.

48) 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

Hide Answer Workspace

Answer: b) Mutation

Explanation: Mutation can be defined as a change in the DNA that is responsible for
bringing about benefits, harm, or nothing.

49) Which of the following is the best representation of individual genes?

a. Coding

b. Conversion
c. Encoding

d. None of the above

Hide Answer Workspace

Answer: c) Encoding

Explanation: Encoding is a process of transmuting phenotype space to genotype


space.

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

Hide Answer Workspace

Answer: b) Reproduction

Explanation: A genetic algorithm initializes the population by utilizing random values


followed by running each individual from the population through the fitness function.
Then the fittest one gets selected among the population to reproduce by using the
reproduction function. The process of evaluation and reproduction is repeated until a
desired number of iterations have been passed.

51) Name the selection method that is found to be less noisy.

a. Boltzmann solution

b. Remainder solution

c. Stochastic remainder solution

d. None of the above

Hide Answer Workspace

Answer: c) Stochastic Remainder Solution


Explanation: None.

52) In how many steps does a crossover operator proceed?

a. 2

b. 3

c. 4

d. 5

Hide Answer Workspace

Answer: b) 3

Explanation: In a genetic algorithm, the crossover can be entitled recombination,


which is nothing but a genetic operator that associates the genetic information of two
parents to produce a new offspring.

53) 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

Hide Answer Workspace

Answer: c) Output based learning

Explanation: Reinforcement learning is another branch of machine learning that learns


from the output errors and improves them in the subsequent iterations.

54) ________ helps in converting a given bit pattern into another bit pattern by
using logical bit-wise operation.

a. Masking

b. Segregation
c. Conversion

d. Inversion

Hide Answer Workspace

Answer: a) Masking

Explanation: None

55) 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

Hide Answer Workspace

Answer: b) Shift left

Explanation: None

56) 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

Hide Answer Workspace

Answer: b) Steady-state

Explanation: None.
57) ________ deals with uncertainty problems with its own merits and demerits

a. Neuro-fuzzy

b. Neuro-genetic

c. Fuzzy-genetic

d. None

Hide Answer Workspace

Answer: a) Neuro-fuzzy

Explanation: Neuro-fuzzy refers to the amalgamation of neural networks and fuzzy


logic in the field of artificial intelligence. It is nothing but a fuzzy system whose
parameters learn through the learning algorithms acquired from the neural networks.

58) What does FAM stand for?

a. Fuzzy Association Memory

b. Fuzzy Associative Memory

c. Fuzzy Assist Memory

d. None of the above

Hide Answer Workspace

Answer: b) Fuzzy Associative Memory

Explanation: Fuzzy associative memory is a kind of neural network that stores the
associations of patterns. It recalls the stored patterns from the noisy inputs.

59) 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


Hide Answer Workspace

Answer: c) Fuzzy-genetic

Explanation: Fuzzy-genetic can be identified as a system built with the help of genetic
algorithms, assisting in imitating the process of natural evolution, which is necessary
for identifying its parameter and structures.

60) Matrix crossover is also known as _________

a. One dimensional

b. Two dimensional

c. Three dimensional

d. None of the above

Hide Answer Workspace

Answer: b) Two dimensional

Explanation: Matrix crossover initially selects three parents. Then each bit of the first
parent is associated with that of the second parent. If both are found to be similar, then
the bit is taken for the offspring, else the third parent's bit is considered for the
offspring.

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

Answer Report Discuss


Option: A

Explanation :

Click on Discuss to view users comments.


2: Who initiated the idea of Soft Computing
A.Charles Darwin

B. Lofti A Zadeh

C.Rechenberg

D.Mc_Culloch

Answer Report Discuss


Option: B

Explanation :

Click on Discuss to view users comments.

3: Fuzzy Computing
A.mimics human behaviour

B. doesnt deal with 2 valued logic

C.deals with information which is vague, imprecise, uncertain, ambiguous,


inexact, or probabilistic

D.All of the above

Answer Report Discuss


Option: D

Explanation :

Click on Discuss to view users comments.

4: Neural Computing
A.mimics human brain

B. information processing paradigm

C.Both (a) and (b)

D.None of the above

Answer Report Discuss


Option: C

Explanation :
Click on Discuss to view users comments.

5: 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

Answer Report Discuss


Option: D

Explanation :

Click on Discuss to view users comments.

UNIT – I

1. The structural constitute of a human brain is known as ------------------

a. Neuron b)Cells c)Chromosomes d)Genes

2.Neural networks also known as -----------------------

a)Artificial Neural Network b)Artificial Neural Systems


c)Both A and B d) None of the above

3. Neurons also known as -----------------

a)Neurodes b)Processing elements c)Nodes d)All the above

4. In the neuron, attached to the soma are long irregularly shaped filaments called--------------

a)Dendrites b)Axon c)Synapse d)Cerebellum

5. Signum function is defined as -------------------

a) φ(I) =+1, I>0, -1, I<=0

b) φ(I)=0

c) φ(I)=+1,I>0

d) φ(I)=-1,I<=0

6. To generate the final output, the sum is passed on to a non-linear filter φ called

a)Smash function b)sum function c)Activation function d)Output function


7. ---------------function is a continuous function that varies gradually between the asymptotic values 0
and 1 or -1 and +1

a)Activation function b)Thresholding function c)Signum function d)Sigmoidal function

8.-----------------produce negative output values

a)Hyperbolic tangent function b)Parabolic tangent function

c)Tangent function d)None of the above

9.-------------------- carrying the weights connect every input neuron to the output neuron but not vice-
versa.

a)Feed forward network


b)Fast forward network
c)Fast network
d)Forward network
10.------------- has not feedback loop

a)Neural network b)Recurrent Network c)Multilayer Network d)Feed forward network

11. In the learning method, the target output is not presented to the network ----------------

a) Supervised learning b)Unsupervised learning

c)Reinforced learning d)Hebbian learning

12. Combining a number of ADALINE is ----------------

a) MULTILINE b)MULTIPLE LINE C)MADALINE d)MANYLINE

13.Neural network applications -----------------

a) Pattern Recognition b)Optimization Problem c)Forecasting d)All the above

14.------------------ is a Systematic method for training multilayer artificial neural network

a)Back propagation b)Forward propagation c)Speed propagation d)Multilayer propagation

15. --------------------- is a computational model

a) neuron b) cell c)Perception d)Neucleus

16.Intermediatry layer is present in ----------------------

a)Multilayer feedforward perception model

b)Multilayer perception model

c)Multilayer Feedforward model

d)None of the above


17.Linear Activation Operator equation is ---------------

a) O=gI,g=tanφ

b) O=gI,g=sinφ

c) O=gI,g=cosφ

d) O=gI,g=-tanφ

18.--------------- is never assured of finding global minimum as in the simple layer delta rulecase.

a)Back propagation b)Front Propagation c)Propagation d)None above

19.The test of neural network is known as--------------

a)Inference Engine b)Checking c)Deriving d)None

20.Application of Back Propagation

a)Design of Journal Bearing b)Classification of soil

c)Hot Extrusion of soil d)All the above

21. Reinforced learning also known as ----------------

a)Output based learning b)Error based learning

c)Back propagation learning d)None

22.---------------------learning follows “Winner takes all” strategy

a)Stochastic learning b)Competitive learning c)Hebbian learning d)BackPropagation learning

23.------------------earlier neural network architecture,

a)Rosenblatt Perception b)Rosen Perception c)Roshon Perception d)None

24. In Rosenblatt’s Perception network has three units, sensory unit, association unit and --------------
a)Output unit b) Response unit c) feedback unit d) Result unit

25.ADALINE stands for --------------------------

a)Adaptive Linear Neural Element Network

b)Adaptive Line Neural Network

c)Adapt Line Neural Element Network

d)Adaptive Linear Neural Network

PART-B
1. Explain model of artificial neuron
2. Differentiate Learning methods supervised, unsupervised, and reinforced learning
3. Explain Rosenblatt’s Perception
4. Explain ADALINE network
5. Explain Single layer ANN
6. Explain any one application of Back propagation networks

PART-C

1. Explain neural network architecture


2. Explain back propagation learning briefly
3. Explain basic concepts of neural network

UNIT-2

1.----------------is a store house of associated patterns which are encoded in some form

a)Associative memory b) Commutative memory

c)Neural networks d)Memory

2. If the associated pattern pairs (x,y) are different and if the model recalls a y given an x or vice versa,
then it is termed as -------------

a) Auto associative memory b) Hetero associative memory

c) neuro associative memory d) none

3. Autoassociative correlation memories are known as ---------------

a) Auto correlators b) Hetero Correlators c)Neuro Correlators d) None

4.--------------- recalls an output given an input in one feedforward pass

a)Static networks b) Dynamic networks c)Recurrent networks d) None

5.BAM stands for ----------------

a)Bidirectional Associative Memory b)v Associative Memory

c)Biconventional Associative Memory d) None

6.----------------- associates patterns in bipolar forms that are real-coded

a)Simplified Bidirectional Associative Memory b)Bipolar form

c)Bidirectional form d)None

7)---------------------- uses bipolar coding

a)Fabric defect identification b)Recognition of Characters


c)Design of Journal Bearing d) Classification of soil

8)Self-organizing network also known as ---------------------

a)Back Propagation network b)Training free counter propagation network

c)Propagation network d)none

9)Kesko proposed an energy function for the two states -----------------

a)E(A,B)=AMB T

b)E(A,B)=-AMB T

C)E(A,B)=-AB T

D)E(A,B)=AB T

10) BAM was introduced by ----------------------

a) Cruz b) Stubberd c)Kosko d)Rosenbatt

11)The algorithm which computes operator M is known as ------------------

a)Memory algorithm b)Recording Algorithm c)Transfer Algorithm d)None

12) Real coding is used by -----------------

a)Recognition of characters b)Fabric defect identification

c)Optimization d)Classification of soil

13)ART stands for --------------------

a)Adaptive Resonance Theory b)Adaptive Recent Theory

c)Adapt Resonance Theory d)Adaptive Retail Theory

14)A program --------------- is written in fortran for cluster formation

a) Vecquent b)Vecant c)Vector d)Quantization

15)----------------- networks were developed by carpenter and grossberg

a)ART b)ARP c)ARC d)ARD

16)------------------ of the network means that a pattern should not oscillate among different cluster units
at different stages of training

a)Stability b)Mobility c)Versitality d)Placticity

17)------------------- is the analogus version of ART


a)ART2 b)ART1 c)ART2A d)ARTMAP

18)----------------- test is incorporated into the adaptive backward network

a)Vigilance b)Indulgence c)Revailance d)None

19)In ---------------- learning the weights are adjusted only when the external input matches one of the
stored prototypes

a)Supervised b)UnSupervised c)Match-based d)None

20)Kim et al. Proposed an ------------------ method using ART2 architecture.

a)Pattern Recognition b) Chinese Recognition method

c)Character Recognition d)None

21)--------------- learning weight update during resonance occurs rapidly

a)Error-based b) Fast c)Slow d)Match-based

22)Comparison layer and recognition layer constitute -----------

a)Attenuation b)Attenuated System c)Synaptic System d)None

23)ART1 is an elegant theory that address ------------------

a)Stability – plasticity dilemma

b)Stability dilemma

c)Plasticity dilemma

d)None

24)Supervised version of ART -----------------

a)ARTMAP

b)Fuzzy art

c)Fuzzy Artmap

d)ART1

25)Slow learning is used as -----------------

a)ART1

b)ART2

c)ARTMAP

d)Fuzzy ART
PART-B

1.Explain Auto Correlators

2.Explain HeterCorrelators

3.Explain any one application of associative memory

4.Explain Simplified ART architecture

5.Disitinguish ART1 and ART2

6.Explain any one application of ART

PART-C

7.Explain Exponential BAM

8.Explain Classical ART network

9.Explain ART1 algorithm

1. 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) 000 or 110 or 011 or 101

b) 010 or 100 or 110 or 101

c) 000 or 010 or 110 or 100

d) 100 or 111 or 101 or 001

View Answer

Answer: c

2. 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

View Answer

Answer: a
3. 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

View Answer

Answer: b

4. 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. What will be the output?

a) 238

b) 76

c) 119

d) 123

View Answer

Answer: a

Explanation: The output is found by multiplying the weights with their respective inputs, summing the
results and multiplying with the transfer function. Therefore:

Output = 2 * (1*4 + 2*10 + 3*5 + 4*20) = 238.

5. 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.

a) All of the mentioned are true

b) (ii) and (iii) are true

c) (i), (ii) and (iii) are true

d) None of the mentioned

View Answer
Answer: a

Explanation: Neural networks have higher computational rates than conventional computers because a
lot of the operation is done in parallel. That is not the case when the neural network is simulated on a
computer. The idea behind neural nets is based on the way the human brain works. Neural nets cannot
be programmed, they can only learn by examples.

6. 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.

a) All of the mentioned

b) (ii) is true

c) (i) and (ii) are true

d) None of the mentioned

View Answer

Answer: c

Explanation: The training time depends on the size of the network; the number of neuron is greater and
therefore the number of possible ‘states’ is increased. Neural networks can be simulated on a
conventional computer but the main advantage of neural networks – parallel execution – is lost.
Artificial neurons are not identical in operation to the biological ones.

7. 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

a) (i) and (ii) are true

b) (i) and (iii) are true

c) Only (i)

d) All of the mentioned

View Answer
Answer: d

Explanation: Neural networks learn by example. They are more fault tolerant because they are always
able to respond and small changes in input do not normally cause a change in output. Because of their
parallel architecture, high computational rates are achieved.

8. 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

a) (ii) and (iii) are true

b) (ii) is true

c) All of the mentioned

d) None of the mentioned

View Answer

Answer: a

Explanation: Pattern recognition is what single layer neural networks are best at but they don’t have the
ability to find the parity of a picture or to determine whether two shapes are connected or not.

9. Which is true for neural networks?

a) It has set of nodes and connections

b) Each node computes it’s weighted input

c) Node could be in excited state or non-excited state

d) All of the mentioned

View Answer

Answer: d

Explanation: All mentioned are the characteristics of neural network.

10. What is Neuro software?

a) A software used to analyze neurons

b) It is powerful and easy neural network


c) Designed to aid experts in real world

d) It is software used by Neurosurgeon

View Answer

Answer: b

Explanation: None.

1. 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.

View Answer

Answer: d

Explanation: None.

2. What is back propagation?

a) It is another name given to the curvy function in the perceptron

b) It is the transmission of error 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 mentioned

View Answer

Answer: c

Explanation: Back propagation is the transmission of error back through the network to allow weights to
be adjusted so that the network can learn.

3. 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 class of problem that Perceptron can solve successfully

c) Because they are the only mathematical functions that are continue

d) Because they are the only mathematical functions you can draw

View Answer

Answer: b

Explanation: Linearly separable problems of interest of neural network researchers because they are the
only class of problem that Perceptron can solve successfully.

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

a) It can explain result

b) It can survive the failure of some nodes

c) It has inherent parallelism

d) It can handle noise

View Answer

Answer: a

Explanation: The artificial Neural Network (ANN) cannot explain result.

5. Neural Networks are complex ______________ with many parameters.

a) Linear Functions

b) Nonlinear Functions

c) Discrete Functions

d) Exponential Functions

View Answer

Answer: a

Explanation: Neural networks are complex linear functions with many parameters.

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) True
b) False

c) Sometimes – it can also output intermediate values as well

d) Can’t say

View Answer

Answer: a

Explanation: Yes the perceptron works like that.

7. What is the name of the function in the following statement “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) Step function

b) Heaviside function

c) Logistic function

d) Perceptron function

View Answer

Answer: b

Explanation: Also known as the step function – so answer 1 is also right. It is a hard thresholding
function, either on or off with no in-between.

8. Having multiple perceptrons can actually solve the XOR problem satisfactorily: this is because each
perceptron can partition off a linear part of the space itself, and they can then combine their results.

a) True – this works always, and these multiple perceptrons learn to classify even complex problems

b) False – perceptrons are mathematically incapable of solving linearly inseparable functions, no matter
what you do

c) True – perceptrons can do this but are unable to learn to do it – they have to be explicitly hand-coded

d) False – just having a single perceptron is enough

View Answer

Answer: c

Explanation: None.
9. The network that involves backward links from output to the input and hidden layers is called
_________

a) Self organizing maps

b) Perceptrons

c) Recurrent neural network

d) Multi layered perceptron

View Answer

Answer: c

Explanation: RNN (Recurrent neural network) topology involves backward links from output to the input
and hidden layers.

10. Which of the following is an application of NN (Neural Network)?

a) Sales forecasting

b) Data validation

c) Risk management

d) All of the mentioned

View Answer

Answer: d

Explanation: All mentioned options are applications of Neural Network.

You might also like