mnn_device.asv

基于BP模型的神经网络模型

%~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
%
%  mNN_device(n,date,iterations) - gradient descent procedure for Matrix
%  neural network training.
%  
%  Parameters: network -  neural network with matrix networks
%              data - training data sample
%              iterations - how many iterations to perform training
%
%  Author: Povilas Daniu餴s, [e-mail]
%  http://ai.hacker.lt - lithuanian site about Artificial Intelligence.
%
%  TODO: weighted MSE minimization, maximal likelihood method, multiple
%  activation function support.
%  ----------------------------------------------------------------------

function f = mNN_device(n,alpha,msize)

ro = msize(1);
co = msize(2);
 
for i=1:n
    left(i).w = alpha*(2*rand(1, ro) - 1);
    right(i).w = alpha*(2*rand(co, 1) - 1); 
    d_left(i,:) = zeros(1,ro);  %derivatives
    d_right(i,:) = zeros(co,1);
    dleft(i,:) = zeros(1,ro);   %deltas
    dright(i,:) = zeros(co,1);
end    

f.regressors = n;
f.left = left;
f.right = right;
f.d_left = d_left;
f.d_right = d_right;
f.dleft = dleft;
f.dright = dright;
f.d_b = zeros(1,n);
f.weights = 2*rand(1,n+1) - 1;
f.dweights = zeros(1,n+1);
f.d = zeros(1,n+1);
f.bias = alpha*(2*rand(1,n) - 1);
f.dbias = zeros(i,n);
f.numparams = n+1 + n*(ro + co + 1);