You are on page 1of 1

Assignment Sheet 2

ICE-328 Neural Networks and Fuzzy Logic


Date: 24th March 2014

1. Solve using the MAXICAN HAT net algorithm for the given data .
The co-operative and competitive net radius is given by R1=2 and R2=4. The initial
weights are C1=0.8 and C2=-0.5.
The external signal is given as x=(0.0, 0.3, 0.4, 0.6,0.2, 0.15,0.1).
2. Use the Kohenen Self Organizing Map algorithm for the given data.
The four cluster units are given as (0,1,1,0); (1,1,1,0);(0,0,1,1) and (1,0,01). The
maximum no. of clusters to be formed is m=2, the learning rate =0.4. Also the initial
0.1 0.5
0.2 0.1
. Solve for 5 iterations and write the weights arrived
weight matrix is given as
0.6 0.8

0.4 0.2
at the fifth iteration.
3. Write the m-code and simulate to find the final weights for the perceptron, hebian and Bidirectional Associative Memory algorithms. Consider the inputs and targets as same in
the class black board problem for each algorithm.

You might also like