Scribd
Upload
305 views2 pages

Total Pages: 2: Answer All Questions, Each Carries 3 Marks

This document appears to be an exam for a course on soft computing techniques. It contains questions about various topics in soft computing, including artificial neural networks, fuzzy logic, genetic algorithms, and neuro-fuzzy systems. The exam is divided into multiple parts testing knowledge of concepts such as learning mechanisms in neural networks, training algorithms for perceptrons, fuzzy set operations, fuzzy inference systems, fuzzy propositions, genetic algorithm encoding methods, and genetic-neuro hybrid systems.

Uploaded by

shakirck
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
305 views2 pages

Total Pages: 2: Answer All Questions, Each Carries 3 Marks

This document appears to be an exam for a course on soft computing techniques. It contains questions about various topics in soft computing, including artificial neural networks, fuzzy logic, genetic algorithms, and neuro-fuzzy systems. The exam is divided into multiple parts testing knowledge of concepts such as learning mechanisms in neural networks, training algorithms for perceptrons, fuzzy set operations, fuzzy inference systems, fuzzy propositions, genetic algorithm encoding methods, and genetic-neuro hybrid systems.

Uploaded by

shakirck
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/ 2

F F7190

Total Pages: 2
Reg No.:_______________ Name:__________________________

APJ ABDUL KALAM TECHNOLOGICAL UNIVERSITY


THIRD SEMESTER B.TECH DEGREE EXAMINATION, DECEMBER 2017
Course Code: CS361
Course Name: SOFT COMPUTING (CS)
Max. Marks: 100 Duration: 3 Hours
PART A
Answer all questions, each carries 3 marks. Marks
1 Explain the different learning mechanisms used in Artificial Neural Networks (3)
with the help of necessary diagrams.
2 With the help of an example, state the role of bias in determining the net output (3)
of an Artificial Neural Network.
3 Illustrate the different steps involved in the training algorithm of Perceptrons. (3)
4 State the concept of delta-rule used in Adaptive Linear Neurons. (3)
PART B
Answer any two full questions, each carries 9 marks.
5 Design a Hebb network to realize logical OR function. (9)
6 Implement AND logical function using Perceptrons. (9)
7 a) How is the training algorithm performed in back-propagation neural networks? (5)
b) With graphical representations, explain the activation functions used in Artificial (4)
Neural Networks.
PART C
Answer all questions, each carries 3 marks.
8 List and explain the various operations that can be performed in fuzzy relations. (3)
9 Law of contradiction and law of excluded middle cannot be applied to fuzzy sets. (3)
Give proper justification to the statement.
10 With the help of a figure, explain the features of fuzzy membership functions. (3)
11 How can the role of lambda-cuts in defuzzification be justified? Give examples. (3)
PART D
Answer any two full questions, each carries 9 marks.
12 a) . . (4)
Given two fuzzy sets, M˷ and N˷, such that M˷ = + + + +
. . . .
and N˷ = + + + + + + . Construct a relation
R˷ = M˷ x N˷.
b) . . (5)
Introduce another fuzzy set M1˷= + + + + . Find M1˷o R˷
using max-min composition.
13 a) Consider the following two fuzzy sets: (4)
. . . .
A˷ = + + +

Page 1 of 2

For More Visit : KtuQbank.com


F F7190

. . .
B˷ = + + +
Find the algebraic sum, algebraic product, bounded sum, and bounded difference
of the given sets.
b) Using inference method, find the membership values of the triangular shapes; (5)
isosceles (I), right angled (R), isosceles and right angled (IR), equilateral (E), and
other triangles (T); for a triangle with angles 60, 55, and 65.
14 a) 1 0.8 0 0.1 0.2 (4.5)
⎡0.8 1 0.4 0 0.9⎤
⎢ ⎥
Consider the following fuzzy relation, R˷ = ⎢ 0 0.4 1 0 0⎥
⎢0.1 0 0 1 0.5⎥
⎣0.2 0.9 0 0.5 1 ⎦
Show that the above relation is a tolerance relation.
b) Also, show that the λ-cut relation of the above relation results in a crisp tolerance (4.5)
relation.
PART E
Answer any four full questions, each carries 10 marks.
15 a) “A compound rule may be decomposed and reduced into a number of simple (6)
canonical rule forms”. Explain the different methods to do so.
b) How can one perform the aggregation of fuzzy rules? (4)
16 With the help of necessary block diagrams, compare Mamdani and Sugeno (10)
Fuzzy Inference Systems.
17 a) With the help of examples, explain the various fuzzy propositions. (6)
b) Explain the different methods for fuzzy approximate reasoning. (4)
18 a) Explain the different methods of encoding that are possible in genetic algorithm. (6)
b) “Termination criterion for a genetic algorithm brings the search to a halt”. (4)
Explain the various termination techniques.
19 With the help of examples, explain the various crossover techniques employed in (10)
genetic algorithms.
20 a) Illustrate the different steps in genetic-neuro hybrid systems with the help of a (6)
neat block diagram.
b) Distinguish between the processes of tuning and learning in genetic-fuzzy rule (4)
based systems.
****

Page 2 of 2

For More Visit : KtuQbank.com

You might also like