Reg No.:

Max. Marks: 100

12

13

a)
b)

a)

b)

F7190

Total Pages: 2

Name:

APJ ABDUL KALAM TECHNOLOGICAL UNIVERSITY
THIRD SEMESTER B.TECH DEGREE EXAMINATION, DECEMBER 2017
Course Code: CS361
Course Name: SOFT COMPUTING (CS)

PART A
Answer all questions, each carries 3 marks.

Explain the different learning mechanisms used in Artificial Neural Networks
with the help of necessary diagrams.
With the help of an example, state the role of bias in determining the net output
of an Artificial Neural Network.
Illustrate the different steps involved in the training algorithm of Perceptrons.
State the concept of delta-rule used in Adaptive Linear Neurons.

PART B

Answer any two full questions, each carries 9 marks.

Design a Hebb network to realize logical OR function.
Implement AND logical function using Perceptrons.
How is the training algorithm performed in back-propagation neural networks?
With graphical representations, explain the activation functions used in Artificial
Neural Networks.
PART C
Answer all questions, each carries 3 marks.

List and explain the various operations that can be performed in fuzzy relations.
Law of contradiction and law of excluded middle cannot be applied to fuzzy sets.
Give proper justification to the statement.
With the help of a figure, explain the features of fuzzy membership functions.
How can the role of lambda-cuts in defuzzification be justified? Give examples.
PART D
Answer any two full questions, each carries 9 marks.
1

0 0.8 0.8
Given two fuzzy sets, M_ and N_, such that M_ = {= + பம
x1 x2 x3 x4

0 0 0.2 0.7 1 0.7 0.2 0 ⋅
யப N {~ + -- + -- + ಕಾರಾ + -- + tt <} Construct a relation
x5 ~ (11 y2 y3 y4 ys 36 377

0 0.8 1 0.6 0 ⋅

Introduce another fuzzy set Mi -{— + -- + -- + ம்ம்‌ 3 Find 17൨0 २.
x1 x2 x3 x4 x5

using max-min composition.

Consider the following two fuzzy sets:

0.2 0.3 0.4 0.5
1. 1.1.)

Page 1 of 2

Duration: 3 Hours

Marks

(3)
(3)

(3)
(3)

(9)
(9)
(5)
(4)

(3)
(3)

(3)
(3)

(4)

(5)

(4)