Download AKTU B-Tech 3rd Sem 2015-2016 031EOE Introduction To Soft Computing Neural Networksfuzzy Logic And Genetic Algorithm Question Paper

Download AKTU (Dr. A.P.J. Abdul Kalam Technical University (AKTU), formerly Uttar Pradesh Technical University (UPTU) B-Tech 3rd Semester (Third Semester) 2015-2016 031EOE Introduction To Soft Computing Neural Networksfuzzy Logic And Genetic Algorithm Question Paper

Printed Pagesz-4 95 NOE031/EOE-03l
(Following Paper ID and Roll No. to be ?lled' In your
Answer Book)
Roll No.
B.TECH
Paper ll) :l99351/
19936}
(SEM. III) THEORY EXAMINATION, 2015-16
INTRODUCTION TO SOFT CONEPUTING
(NEURAL NETWORKS, FUZZY LOGIC AND
GENETIC ALGORITHM)
[Time:3 hours] J [MaximumMafksleO]
SECI'ION?A
Note : Attempt a_ll parts. All parts carry equal marks. Write
answer of each part in short. (2 X 10:20)
1. (a) What are neurons?
(b) Give the difference between supervised and
unsupervised learning in arti?cial neural network?
(c) What is difference between auto associative
memory and hetero associative Memory?
(d) Explain binaty encoding in genetic algorithm.
(e) Which neural network architecture is used for On
line spell checking?
' 8200 (1) I P110.

(f) Consider an auto associative net with the bipolar step
?mction as the activation function and weights set
by Hebb rule (outer diagonal) where the main
diagonal of the weight matrix is set to zero. Find the
weight matrix to store the vector V5? 1 1 1 -1 -1).
(g) What is inheritance in genetic algorithm?
(h) If the net input to an output neuron is 0.64,
calculate its output when the activation function is
binary sigmoidal.
(i) What is the difference between crisp set and fuzzy
set?
(i) Name any three commercial so?ware used for soft
computing techniques.
SECTION-B
Note: Attempt any ?ve questions from this section. ?
8200
(10x5=50)
Consider three orthogonal vectors [1 -1 1-1]
[-1 1 1-1] [1 1?1 -l]. Find the weight matrix to store
all the three orthogonal vectors and test the response
of the net for each of the input vectors given. ?
Why mutation is done in genetic algorithm? Explain
types of mutation.
Explain two point crossover and uniform crossover in
genetic algorithm.
(2) NOE-031/EOE?O31
Explain McCulloch-Pitts Neuron model and write -
disadvantage of it. '
Explain the topology and learning in Bidirectional
Associative Memory. '
For the given input vectors S=(Sl, Sz, 82, S 4) and output
vectors t=(tl, t2), ?nd the weight matrix using hetero?-_
associative training algorithm.
s:(sl, 32, 82, 34) 1:01, 12),
I=(1 0 1 0) (1,0)
11=(1 1 0 0) (1, 0)
[11=(1 1 1 0) (0, 0)
1V=(1 0 0 0) (0, 1) ,
Write bene?ts of genetic algorithm. Explain the back-
progagation algorithm.
Explain Hebbian learning.
SECTION-C
Note: Attempt aily m_g questions from this section. -
10.
8200
(15x2=30)
(a) Explain the structure of Boltzmann Machine. Why
is it not proven useful for practical problems in
. machine learning or inference?
' (b) Draw and Explain the multiple perceptron with its
learning algorithm.
(3) P.T.O.

ll.
12.
8200
(C)
(a)
(b)
(e)
(a)
(b)
(C)
('i') Use the Hebb rule of discrete BAM, ?nd the
weight matrix to store the following (binary)
input output pattern paris.
S(I)=(1,1,0) t(1)=<1 0)
S(Z)=(0,1,0) 1(2)=(0,1)
(ii) Using binary and bipolar step functions as the
activation functions test the response of th?
According to which rule each neuron updates its
state in Hop?eld network? What is the dynamic
behavior of Hop?eld network?
Write vaiious steps of the back propagation
algorithm.
For an air conditioner what will be the input and
output in a Fuzzy controller? '
What is called supervised and unsupervised
training?
Draw and Explain the multiple perceptron with its '
learning a1 gonthm
Write short note on Adaline and Madaline
networks.
(4) NOE-031/EOE-031