ptupaper.com
Roll No……
Total No. of Questions: 08
M. Tech.
(ECE) (Sem.-1st)
NEURAL
NETWORKS & FUZZY LOGIC
Subject
Code: EC-505
Paper
ID: [E0497]
Time: 3 Hrs. Maximum
Marks:100
Instruction to Candidates:
1. Attempt
any FIVE questions out of EIGHT questions.
2. Each question
carry TWENTY marks.
Q1.
(a) Draw and
explain Hardware model of continuous Hopfield network.
(b) Discuss
Energy function of continuous Hopfield network.
Q2.
(a) Explain
the architectures of Counter-Propagation Networks and their training
Algorithms.
(b) Write in
detail about the advantages and disadvantages of artificial neural Networks.
Q3.
Explain the architectures of popular self-organizing maps. Derive the training
algorithm of Kohonen network. Also explain how SOMs can be used for data
compression?
Q4.
(a) Illustrate
with a net Figure, the two basic units of ART network.
(b) Explain
the fault tolerance in neural networks.
Q5.
Define fuzzy set theory. How fuzzy set are different from Crisp set? Explain
with examples. Explain fuzzy union and fuzzy intersection.
Q6.
(a) What are
the industrial applications of Fuzzy logic?
(b) Explain
lambda cuts for fuzzy sets and fuzzy relations.
Q7. What
is difference between FKBC and PID Control? Explain Fuzzy-c means algorithm
with examples.
Q8. Write a short note on any two:
(a) Defuzzyfication
(b) K-means
clustering Algorithm
0 comments:
Post a Comment
North India Campus