JNTU Previous Papers B.Tech CSE 4th Year Neural Networks Apr/May 2008

JNTU B.Tech II Semester Examinations, NEURAL NETWORKS, Apr/May 2008

(Computer Science & Engineering)

Time: 3 hours Max Marks: 80

SET-I

Answer any FIVE Questions

All Questions carry equal marks

1. Explain the simple model of machine learning. With an example. [16]

 

2. Consider the following ortho normal sets of key patterns, applied to a correlation

matrix memory

x1 = [1,0,0,0]T

x2 = [0,1,0,0]T

x3 = [0,0,1,0]T

and respective stored patterns are

y1 = [5,1,0]T

y2 = [-2,1,6]T

y3 = [-2,4,3]T

(a) Calculate the memory matrix

(b) The stimulus applied to the memory is a noisy version of the key pattern x,as shown by

x = [0.8, -0.15,0.15,-0.20]T

Calculate memory response y. [8+8]

 

3. (a) Explain in detail about adaptive filter problem.

(b) Explain in detail about unconstrained orgaizational techinques [8+8]

 

4. Explain signal flow graphical summary of back propagation learning showing forward pass and backward pass. [16]

 

5. (a) What is over fitting? Explain the effects of over fitting on generalization.

(b) Explain variants of cross validation tool. [8+8]

 

6. Write short notes on computer simulations to explain the behavior of self organization map algorithm. [16]

 

7. Discuss about the stability property of the dynamical system taking an example. [16]

 

8. (a) What is the Hopfield network? Explain.

(b) Describe how Hopfield network can be used to have analog to digital conversion. [4+12]

Leave a Comment