# JNTU Question Papers

## Neural Networks 1st Sem Apr/May 2008

1. Write the various benefits of neural networks. Explain them in detail. [16]

2. (a) Explain in detail about competitive learning.

(b) Explain in detail about Bolltzmann learning. [8+8]

3. (a) Explain method of steepest descent for unconstrained optimization.

(b) Explain Newton’s method for unconstrained optimization. [16]

4. Explain in detail about the following methods which are useful in improving back propagation algorithm.

(a) Tangent values

(b) Normalizing the inputs. [8+8]

5. (a) What are the steps involved in the back propagation algorithm. Explain

(b) What are the pattern recognition tasks that can perform by back propagation network. Explain Briefly

(c) What are the limitations of back propagation algorithm? [8+4+4]

6. Determine the Self organization map generated by points selected at random from

an annular ring formed by two concentric circles, consider the following two cases.

(a) The units in the Self organization map are arranged in a 2-dimensional plane.

(b) The units in the self organization map are arranged in 1-dimensional layer. [8+8]

7. Restate Lyapunov’s theorems for the state vector x(0) as the equilibrium state of

a dynamical system. [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]

Above 4