Code covered by the BSD License  

Highlights from
Simple DIP demos

image thumbnail
from Simple DIP demos by Tan Chin Luh
Simple DIP demo using MATLAB 6.1, Image Processing Toolbox and NN Toolbox.

creatnn(arg1,arg2)
function [net,tr] = creatnn(arg1,arg2)

NNinput = arg1;
NNtarget = arg2;
S1 = 80;
S2 = 10;

net = newff(minmax(NNinput),[S1 S2],{'logsig' 'logsig'},'traingda');
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 = 0.01;     % 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,tr] = train(net,NNinput,NNtarget);

Contact us at files@mathworks.com