% xor_2hid.m
% 2/21/09: modified for new Version 6 Toolbox
% Date: 2/3/03 Modified xor_1hid.m for XOR
% Author: G. Dempsey, Bradley Univ.- Electrical Engineering 

% redefine pattern/targets for tansig neurons

close all
clc
clear

% PROBLEM DEFINITION
%===================

y1=[-1 -1]';
y2=[-1 1]';
y3=[1 -1]';
y4=[1 1]';
P=[y1 y2 y3 y4];

% Define targets.

T=[-0.9 0.9 0.9 -0.9];

% INITIALIZE NETWORK ARCHITECTURE
%================================

% Set input vector size R, layer sizes S1, S2 & S3.

S1=2;		% 2 hidden neurons, 1st layer
S2=2;		% 2 hidden neurons, 2nd layer
S3=1;		% single nonlinear output neuron 
R=2;		% number of input components, note parameter
			% not used by training fcn, but good documentation

% Initialize weights and biases. Nyguyen/Widrow method is the default
% initialize the network with single command
% function newff for Version 5.0 Toolbox: enclosed in ***********
%****************************************************************
%net=newff([-1 1;-1 1],[S1,S2,S3],{'tansig','tansig','tansig'},'traingdx');
%****************************************************************

% initialize the network with single command
% function newff for Version 6 Toolbox: enclosed in ***********
%*********************************************************************
net=newff(P,T,[S1,S2],{'tansig','tansig','tansig'},'traingdx');    % BP with adaptive learning and momentum
net.divideFcn = '';                 % don't divide input data into test and validation data
net.inputs{1}.processFcns={};       % don't perform advanced preprocessing
net.outputs{2}.processFcns={};      % don't perform advanced postprocessing
%net.trainParam.showWindow = false; % this will disable TRAIN GUI
%net.trainParam.showCommandLine = true; % this will enable status in command window
%**********************************************************************

% save a copy of the weights/biases from newff
W10=net.IW{1,1};
B10=net.b{1};
W20=net.LW{2,1};
B20=net.b{2};
W30=net.LW{3,2};
B30=net.b{3};

% Output INITIAL ANN Output
%====================================
A=sim(net,P)

disp('press any key to start training')
pause;

% TRAIN THE NETWORK
%==================

% TRAINING PARAMETERS
net.trainParam.show=50;					% display update
net.trainParam.lr=0.01;					% learning rate
net.trainParam.epochs=2000;			% max epochs
net.trainParam.goal=0.02;				% error goal
net.trainParam.lr_inc=1.05;			% lr increase
net.trainParam.lr_dec=0.7;				% lr decrease
net.trainParam.mc=0.95;					% momentum
net.trainParam.max_perf_inc=1.04;	% error ratio check for weight discard

% Now train the ANN
[net,tr]=train(net,P,T);

disp('Press key to see final results')
pause

% summarize 
fprintf('\nFINAL NETWORK VALUES:\n')
W1=net.IW{1,1}	% input to hidden layer weights
B1=net.b{1}		% 1st hidden neuron biases
W2=net.LW{2,1}	% 1st hidden to 2nd hidden layer weights
B2=net.b{2}		% 2nd hidden neuron biases
W3=net.LW{3,2}	% 2nd hidden to output
B3=net.b{3}		% output neuron bia

A=sim(net,P)	% show ANN output with converged weights

fprintf('Trained for %.0f epochs.\n',max(tr.epoch))
fprintf('Mean square error goal was %g.\n',net.trainParam.goal)
fprintf('Final mean square error is %g.\n',tr.perf(max(tr.epoch+1)));
fprintf('Trained network operates: ');
if tr.perf(max(tr.epoch+1))< net.trainParam.goal
  disp('It works!')
else
  disp('It Failed!')
  end

disp('press any key to continue')
pause;

% PLOT Adaptive learning rate CURVE
%=================
figure
disp('plot learning rate curve');
plot(tr.lr);
title('Adaptive Learning Rate Versus Epochs');
xlabel('Epochs');
ylabel('Learning Rate');