Download AKTU B-Tech 3rd Sem 2016-2017 NOE 031 Ntroducation To Soft Computing Neural Networks Fuzzy 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) 2016-2017 NOE 031 Ntroducation To Soft Computing Neural Networks Fuzzy Logic And Genetic Algorithm Question Paper

Printed Pages: 4 NOE - 031
(Following Paper ID and Roll No. to be ?lled in your
Answer Books)
Paper ll) : 2289398 Roll No,
B.TECH
Regular Theory Examination (Odd Sem -III), 2016-17
INTRODUCTION TO SOFT COMPUTING
(NEURAL NETWORKS, FUZZY LOGIC AND
GENETIC ALGORITHM)
T ime : 3 Hours Max. Marks : 100
Note : Attempt all Sections. If require any missing data; then
choose suitably.
SECTION -A
1. Attempt all questions in brief. (10x2=20)
a) Compare soft computing vs. hard computing.
b) De?ne supervised. and unsupervised learning in
arti?cial neural network.
0) ?What do you mean by Neural Network architecture?
(1) What are the disadvantages of fuzzy systems?
e) What is the difference between crispest and fuzzy
set?
f) De?ne mutation.
031/12/2016/11800 (1) [P.T.O.

NOE - 031
g) ' What is leaky learning?
h) Name some application of competitive learning
network.
i) De?ne a F uzzy Cartesian product.
a j) De?ne genetic algorithm and write down the
advantages of GA.
SECTION - B
Attempt any three of the following : (3X10=30)
a) Write the algorithm for back propagation for back
propagation training and explain about the updation
of weight.
b) Can a two inputAdeline compute the XOR function?
How will you solve the same by using Madeline?
c) Draw the block diagram of a Fuzzy logic system,
and define membership function?
d) What are the advantages and disadvantages of hybrid
fuzzy controller in soft computing?
e) Explain two point crossover and uniform crossover
in genetic algorithm
SECTION - C
Attempt any one part of the following : (1X10=10)
a) Draw an artificial neural network. Explain
supervised & unsupervised learning in arti?cial
neural network.
. 031/12/2016/11800 (2)
NOE - 031
b) Write short notes on recurrent auto associative
memory & explain its pros & cons.
Attempt any one part of the following : (1X10=10)
a) Differentiate single layer perceptron method &
multilayer perceptron method.
b) Describe brie?y the architecture of Hop?eld
Network.
Attempt any one part of the following : (1X10=10)
a) For an air conditioner what will be the input and
output in a Fuzzy controller?
b) Given a conditional and quali?ed F uzzy proposition
- ?P? ofthe form. P: Ifx is A, then y is B is S where
?S? is fuzzy truth quali?er and a fact is in the form
?x is A? We want to make an inference in the form
?y is B?. Develop a method based on the truth-value
restrictions for getting the inference.
Attempt any one part of the following : (1X10=10)
a) Explain the industrial applications of fuzzy logic.
b) Use the Hebb rule of disciete BAM, ?nd the weight
matrix to store the followin g (binary) input output
pattempairs.
S(1)=(1,1,0) t(l)=(10)
S(2) = (0, 1, 0) t(2) = (0, 1)
031/12/2016/11800 (3) [P.T.O.

NOE ? 031
7. Attempt any one part of the following : (IX 10=10)
a) Explain optimization 0ftravelling salesman problem
using genetic algorithm and give a suitable example
too.
b) . Draw a ?owchart of GA'& explain the working
principle.
++++
031/12/2016/11800 (4)