Scribd
Upload
105 views3 pages

Hoursl:: Computii (G (I/Eural Logic Ai (D Gei/Etic Algorithm) (Totalmarks:Lq0

This document is a 3 page exam for a course on Introduction to Soft Computing covering neural networks, fuzzy logic, and genetic algorithms. It contains 7 sections with multiple choice, short answer, and numerical problems. Section A has 10 multiple choice questions worth 2 marks each on neural network topics. Section B has 4 short answer problems worth 10 marks each, two focused on neural networks and two on genetic algorithms. Section C has 5 short answer problems worth 10 marks each covering additional neural network and fuzzy logic topics. Sections D-F each have 2 short answer problems worth 10 marks each.

Uploaded by

abhishek
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
105 views3 pages

Hoursl:: Computii (G (I/Eural Logic Ai (D Gei/Etic Algorithm) (Totalmarks:Lq0

This document is a 3 page exam for a course on Introduction to Soft Computing covering neural networks, fuzzy logic, and genetic algorithms. It contains 7 sections with multiple choice, short answer, and numerical problems. Section A has 10 multiple choice questions worth 2 marks each on neural network topics. Section B has 4 short answer problems worth 10 marks each, two focused on neural networks and two on genetic algorithms. Section C has 5 short answer problems worth 10 marks each covering additional neural network and fuzzy logic topics. Sections D-F each have 2 short answer problems worth 10 marks each.

Uploaded by

abhishek
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/ 3

uptuonline.com uptuonline.

com

Printed Pages : 3 EOE041

(Following Paper ID and Roll No. to be filled in your Answer Book)

Roll No.

' B.Tech.
(SEMESTER-I9 THEORY EXAMINATION, 20ll-12
INTRODUCTION TO SOFT COMPUTII{G
(I\EURAL NETWORKS, FTJZZY LOGIC AI{D GEI\ETIC ALGORITHM)

Time:3 Hoursl [TotalMarks:lq0

Note : Answer all the Sections.

Section -A
1. Attempt all the parts. l0 x 2 : 20

(a) Why Neural Networks is also called as Parallel Distributed Processing ?

(b) Define Gradient descent leaming.

(c) Name all types of error based leaming algorithms.

(d) Justify - 'oThe use of adaptive coefficient where the value of the learning
coefficient is the function of error derivative on successive updates."

(e) List all the tuning parameters of the Back-propagation Neural Network.

(f) Define Multiple Training Encoding Strategy.

(g) How to define Power of a Fuzzy Set ?

(h) In propositional logic, name the widely used rules lor inferring facts.

(i) Ilow Genetic algorithms are very different from most of the traditional
optimization methods ?

0) Define Fitness Function in Gas.

0935 P.T.O.

uptuonline.com
http://www.UPTUonline.com
http://www.UPTUonline.com
uptuonline.com uptuonline.com

Section - B

2, Attempt any three parts : 3x l0: 30


(a) What are the characteristics of Neural Networks ? Explain three fundamentally
different classes of Networks.

(b) Explain the selection criteria of various parameters in BpN.

(c) Let X: {ir, b, c, d} Y : U,2,3,4} and A': {(a,0) (b,0.8) (c,0.6) (d, i)}
B' : {(1, 0.2) (2,1) (3, 0.8) (4, 0)} C' : {(1, 0) (2,0.4) (3, 1) (4, 0.8)}
Determine the implication relations
(i) IF x is A' then y is B'
(ii) If x is A' then y is B' else y is C'

(d) Use GA to solve the following non-linear programming problem :

Minimize (xr-2.5)z + (xz - 5)2 subject to 5.5x, + 2xr2 - 18 <:0 0 (: xl,


x2 <:5,
Give three and two decimal places of accuracy to variable xl, x2respectively.
(i) How many bits are required for coding variable ?

(ii) Write down the fitness function which you would be using in reproduction.

Section - C
Attempt all parts. 5x 10:50
3. Attempt any two parts :

(a) Explain Augmented BP Networks with its architecture and transfer function.

(b) Explain the different types of artificial neural networks.

(c) Implement a MADALINE network to solve the XOR problem.

4. Attempt any two parts :

(a) Explain how an auto-correlator results in the refinement of the pattern or removal
of noise to retrieve the closest matching stored pattern.

(b) Explain the Multiple Training Encoding Strategy.

(c) Explain BAM architectures employ bipolar/binary encoding of patterns.

uptuonline.com
http://www.UPTUonline.com
http://www.UPTUonline.com
uptuonline.com uptuonline.com

5. Attempt any two parts :

(a) Explain cartesian product of two sets A & B with example.

(b) A' and B' defined on the intervar


consider the fuzzy sets X : [0, 5] of real
numbers, by the membership grade functions

r;(x) :x /(x +,1), t E (x) :2 *

Determine the mathematical formulae & Graphs of the membership grade


function of each of the following sets :

(i) At, Bt
(ii) AUB
I

(c) Multiply a fuzzy set A by a crisp number a resultsin a new fuzzy set product a.A
with the membership function pu . a. pa(X)
a(X):

6. Attempt any one part :

(a) , Explain Defuzzification and widely used methods.


(b) Explain Fuzzy rule base for the air conditioner control.

7. V/rite short notes on any two :

(a) Roulette-WheelSelection

(b) Cross Over & Inversion


(c) Convergence of GA.

093s

uptuonline.com
http://www.UPTUonline.com
http://www.UPTUonline.com

You might also like