Training an RBFNN using PSO gives same output for any input

2 views (last 30 days)
I have setup an RBFNN using
net = network(1,2,[1;1],[1;0],[0 0;1 0],[0 1])
Then, I have copied the essentials from newrb such as:
net.inputs{1}.size = R;
net.layers{1}.size = Q;
net.inputWeights{1,1}.weightFcn = 'dist';
net.layers{1}.netInputFcn = 'netprod';
net.layers{1}.transferFcn = 'radbas';
net.layers{2}.size = S;
net.outputs{2}.exampleOutput = T;
net = init(net);
At last, I have assigned (assumed) optimum weights (through PSO) to this network 'net' using this:
net.b{1} = b1;
net.iw{1,1} = w1;
net.b{2} = b2;
net.lw{2,1} = w2;
Problem: When I use this network 'net' like this:
Y=net(Input)
Y contains same entries irrespective of the input. I have noticed that each entry of Y is equal to net.b{2}, which is the output bias.
For example:
Y= 6.1397 6.1397 6.1397 6.1397 6.1397.....
What's wrong here?

Answers (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!