Back-propagation algorithm

clear all close all

PATTERNS=[[0.1 0.1 0.13 0.0 0.11 0.15 0.12 0.1 0.01 0.2 0.1 0.1 0.13 0.0 0.11 0.15 0.12 0.1 0.01 0.2];[0.5 0.45 0.6 0.55 0.45 0.55 0.44 0.48 0.5 0.44 0.5 0.45 0.6 0.55 0.45 0.55 0.44 0.48 0.5 0.44];[1 0.9 0.95 1 1 0.9 0.95 .94 1 0.9 1 0.9 0.95 1 1 0.9 0.95 .94 1 0.9]]' %TARGET = [0 0 0 0 0 0 0 0 0 0;0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5;1 1 1 1 1 1 1 1 1 1]; TARGET = [1 0 0;0 1 0;0 0 1] %TARGET = eye(3,3); % Desired output

[g,h]=size(PATTERNS); [m,h]=size(TARGET);

% CREATING and INITIATING THE NETWORK net = newff(minmax(PATTERNS),[5 3],{'logsig','logsig'},'traingdx'); net = init(net); net.LW{2,1} = net.LW{2,1}*0.03; net.b{2} = net.b{2}*0.03;

% TRAINING THE NETWORK net.trainParam.goal = 0.0001; % Sum-squared error goal. net.trainParam.lr = 0.01;% Learning Rate net.trainParam.show = 1; % Frequency of progress displays (in epochs). net.trainParam.epochs = 3000; % Maximum number of epochs to train. net.trainParam.mc = 0.3; % Momentum Factor.

[net,tr] = train(net,PATTERNS,TARGET)

% TEST PATTERNS_TEST=[0.1 0.2 0.15 0.0 0.1 0.1 0.2 0.1 0.13 0.12 0.1 0.2 0.15 0.0 0.1 0.1 0.2 0.1 0.13 0.12;0.5 0.4 0.53 0.55 0.45 0.5 0.4 0.48 0.5 0.44 0.5 0.4 0.53 0.55 0.45 0.5 0.4 0.48 0.5 0.44;1 0.9 0.95 1.05 1 0.9 0.95 1.04 1 0.9 1 0.9 0.95 1 1 0.9 0.95 .94 1 0.9]; for k=1:3 PATTERNS_TEST(:,k); FACE = sim(net,PATTERNS_TEST(:,k)) end

[Adam]

https://uk.mathworks.com/matlabcentral/answers/13205-tutorial-how-to-format-your-question-with-markup#answer_18099

https://uk.mathworks.com/matlabcentral/answers/6200-tutorial-how-to-ask-a-question-on-answers-and-get-a-fast-answer