alphabet,targets] = prprob; %Built in data set in Matlab
plotletters(alphabet); %We wrote this function to display the characters
net = newff(minmax(alphabet),[10 26],{'logsig' 'logsig'},'traingdx');
%These values are set to give better training results (initialization of
%the weights and biases should be small here)
net.LW{2,1} = net.LW{2,1}*0.01;
net.b{2} = net.b{2}*0.01;
net.performFcn = 'sse'; % Sum-Squared Error performance function
net.trainParam.goal = 0.1; % Sum-squared error goal.
net.trainParam.show = 20; % Frequency of progress displays (in epochs).
net.trainParam.epochs = 5000; % Maximum number of epochs to train.
net.trainParam.mc = 0.95; % Momentum constant.
% Training begins...please wait...
P = alphabet;
noisyP=alphabet+randn(size(alphabet))*0.4;
T = targets;
[net,tr] = train(net,P,T);
[net,tr] = train(net,noisyP,T);
%Test on new noisy data
noisyP = alphabet+randn(size(alphabet)) *0.05;
plotletters(noisyP);
A2 = sim(net,noisyP);
for j=1:26 %Number of noisy letters
A3 = compet(A2(:,j));
answer(j) = find(compet(A3) == 1);
end
NetLetters=alphabet(:,answer);
plotletters(NetLetters
);
[RIGHT]على سبيل المثال اريد حفظ الـ net وأريد حفظ الـ answer