sathyabama university - IndiaStudyChannel.com

lovethreewayΤεχνίτη Νοημοσύνη και Ρομποτική

20 Οκτ 2013 (πριν από 4 χρόνια και 19 μέρες)

84 εμφανίσεις


Register Number













SATHYABAMA UNIVERSITY

(Established under section 3 of UGC Act,1956)


Course & Branch : B.E


CSE/
DCS

Title of the Paper :
Neural Networks



Max. Marks:80

Sub. Code :

611701

(2006
-
2007
-
2008)



Time : 3 Hours

Date :07/03/2012







Session :AN

______________________________________________________________________________________________________________________



PART
-

A (10 x 2 = 20)


Answer ALL the

Questions

1.

Define Neural Networks
.


2.

State various Neural Network Architectures?


3.

Give a simple model for an artificial neuron and compare with
normal neuron
.


4.

Differentiate Supervised and Unsupervised learning?


5.

List some of the applications

of Perceptrons?


6.

What are the four major building blocks of Counter Propagation
Network?


7.

What do you meant by XOR Problem?


8.

What do you mean by Delta rule in Back Propagation?


9.

Give the diagrammatic representation of Hopfield network?


10.

De
fine ART and give its applications
.


PART


B



(5 x 12 = 60)

Answer ALL the Questions


11.

Compare and contrast the merits and demerits on Neural
Networks with Biological systems.

(or)

12.

(a) Justify how Neural Networks can be used for pattern
classification.










(8)



(b) Give the characteristics of Inference and Learning.


(4)



13.

Explain the Classification of Neural Network Learning
algorithms with a brief illustration.

(or)

14.

Explain in detail about Perceptron training algorithm
s


15.

Discuss how Back propagation is helpful in reducing the Error by
using Hidden layer in between Input and Output Layer

(or)

16.

Describe the Counter Propagation Network with neat
diagrammatic illustrations.


17.

Explain the Kohonen Network algorithm
in detail.

(or)

18.

State how Neural Networks overcomes Traveling sales man
problem?


19.

What do you mean by Vigilance test in ART and explains its
architecture?

(or)

20.

How do you train Neural Networks to solve the problems in
image processing?