JNTU B.Tech II Semester Examinations, 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

Answer any FIVE Questions

All Questions carry equal marks

SET-III

1. Explain the following benefits of neural network

(a) Neurobiological analogy

(b) Uniformity of analysis and design

(c) Fault tolerance

(d) VLSI implementability. [4+4+4+4]

 

2. (a) Write in detail about error-detection learning.

(b) Write in detail about memory brief learning. [8+8]

 

3. Write about linearly separable patterns and non-linearly separable patterns in single

layer perceptron with an examples [8+8]

 

4. Give the solution for credit -assignment problem using back propagation. [16]

 

5. What is back propagation? Derive its learning algorithm with a schematic two-layer feed forward neural network. [16]

 

6. (a) Explain Willshaw-Vonder malsburg’s of self organized feature map and compare with Kohenen model.

(b) Explain how we can use learning vector quantizer for the final fine tuning of a feature map. [8+8]

 

7. Explain the design procedure of Neuro-Controller for a dynamical system with a case study. [16]

 

8. (a) A Hopfield network made up of 5 neurons, which is required to store the

following three fundamental memories

?1 = {+1, +1, +1, +1, +1}T

?2 = {+1, -1, -1, +1, -1}T

?3 = {-1, +1, -1, +1, +1}T

Evaluate the 5-by-5 synaptic weight matrix of the network

(b) Contrast and compare a recurrent network configuration with a feed forward network. [8+8]

Leave a Comment