- 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/
- Plot the input vectors and initial weights on a unit circle.
- 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.
- Analyze the resulting weights and elaborate on the final weight distribution with respect to the input vectors.
Reviews
There are no reviews yet.