[SOLVED] ECE 449 Assignment 7-Neural network

Description

1. Consider a neural network with two inputs and three neurons in the competitive layer. The input vectors in the training set have the values

x₁ =−1, x₂ =0, x₃ =1/   2 ,

                         

0          1        1/_

and the initial weight vectors are

w₁ =0 , w₂ =− 2/    5, w₃ =−1/   5 .

                                      

−1           1/_            _2/_

1. Plot the input vectors and initial weights on a unit circle.
2. Calculate the resulting weights found after training the neurons with competitive learning rule using learning rate =0.5, on the following sequence of inputs: x₁,x₂,x₃,x₁,x₂,x₃. Note: Weights must always lie on a unit circle, and thus must be re-normalized after each iteration.
3. Analyze the resulting weights and elaborate on the final weight distribution with respect to the input vectors.