Jawaharlal Nehru Technological University Hyderabad 2006-2nd Year B.E Computer Science JNTU B.TECH 4th nd sem Neural Networks sets 1,2,3,4 for Engg - Question Paper

Code No: RR420507 Set No. 1
IV B.Tech II Semester Regular Examinations, Apr/May 2006
NEURAL NETWORKS
( Common to Computer Science & Engineering and Electronics &
Computer Engineering)
Time: three hours Max Marks: 80
ans any 5 ques.
All ques. carry equal marks
? ? ? ? ?
1. What is meant by activation function? An odd sigmoid function is described by
f (V ) = tanh (av/2) where tanh denotes the hyperbolic tangent. [2]
(a) elaborate the limiting values of this function? [3]
(b) obtain the derivative of f (v) with respect to v. [3]
(c) What is the value of this derivative at the origin? [3]
(d) Suppose that the shape parameter a is made infinitely large. What is the
resulting form of f (v)? [5]
2. (a) define perceptron and discuss about its working principle in detail. [2+6]
(b) discuss the limitations of perceptron? [8]
3. Generalize the XOR issue to a parity issue for N(>2) variables by considering
a network for the 2 variables 1st and then extending the network considering
the output of the 1st network as 1 variable and the 3rd variable as a different.
Repeat this for n=4 and design a network for solving the parity issue for 4
variables. [8+8]
4. elaborate the modes of operation of a Hopfield network? discuss the algorithm for
storage of info in a Hopfield network. Similarly discuss the recall algorithm.
[4+8+4]
5. (a) discuss the architecture and training of Kohonen’s self-organizing network.
[3+5]
(b) discuss the Kohomem’s learning algorithm. [8]
6. discuss the bidirectional associative memories using suitable examples for storage
algorithms. [4x4]
7. provide a detailed note on the following:
(a) ART1 data structures. [8]
(b) ART2 simulation. [8]
8. define how a neural network may be trained for a trend recognition task.
Illustrate with an example [16]
? ? ? ? ?
1 of 1
Code No: RR420507 Set No. 2
IV B.Tech II Semester Regular Examinations, Apr/May 2006
NEURAL NETWORKS
( Common to Computer Science & Engineering and Electronics &
Computer Engineering)
Time: three hours Max Marks: 80
ans any 5 ques.
All ques. carry equal marks
? ? ? ? ?
1. (a) Consider a multilayer feed forward network, all the neurons of which operate
in their linear regions. Justify the statement that such a network is equivalent
to a single layer feed forward network. [8]
(b) What is the advantage of having hidden layers in an ANN? On what basis is
the number of hidden layers and the number of neurons in every hidden layer
selected? [3+5]
2. (a) define perceptron and discuss about its working principle in detail. [2+6]

Earning:   Approval pending.