example1.m

基于BP模型的神经网络模型

%~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
%
%  Data fitting DEMO of neural networks with matrix inputs.
%
%  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.
%  ----------------------------------------------------------------------

clear all

alpha = 0.9;       % inertia
eta = 0.005;       % inital learning rate
epsilon = 0.03;    % needed MSE
epsilon1 = 0.001;  % minimal descent (stopping criteria) - all iterations in this case
neurones = 20;    % su 20 neveikia :) 
n = 10;
numEpochs = 30;
earlyStop = 5;      


for i=1:100
    x = rand(1,49   );
    data.training(i).mat = reshape(x,7,7);
 %   data.target(i) = sin(x(1) + exp(x(2))) + 2*cos(x(3) + x(4)) + (1 + x(5)^2 + x(6)^2)/(1 + x(5)^2 + x(6)^2);
    data.target(i) = sin(trace(data.training(i).mat));
   %  data.target(i) = sin(mean(x));
end

%data.vtraining = data.vtraining';

e = mNN_device(neurones,size(data.training(1).mat),alpha,eta,epsilon,epsilon1,earlyStop);
e_elm = ELM_train(e,data); 
%e_elm = gdtrain(e,data,10);

s_elm = mNN_sim(e_elm,data);

plot(data.target,'r-'); hold on;
plot(s_elm,'b-');

sum((data.target - s_elm).^2) / length(data.target)