Im now up in the fifth rewrite. Hehe, I truly rock dont I? [smile]
Anyways, I think I got a better structure for the net now, easier to understand. However the training part doesnt seem to be working as intended. Ive tried everything, stepping through with debugger, doing cout's after every line, taking breaks and coming back to the code etc. Nothing seems to be working. Anyone care to take a look? Its not a long code.
Heres how it works, x(l,n) returns whatever neuron n in layer l fired, n == 0 is the bias, 1. The function w(l,f,n) returns the weight assigned to the input f for neuron n on layer l. If f == 0 its the bias weight.
I start every training run with calling the function Process(), the only thing it does is calculating the x (outputs) of every neuron in the net so that when I train, I train on the new outputs calculated from the new weights.
Heres the code; although the only part relevant is Train(), I left the other stuff in (except for some logging) for reference if you couldnt understand my description above. :P
#include "NeuralNet.h"
NeuralNet::NeuralNet(int _Inputs, int _NeuronsInHidden, int _Outputs) {
Inputs = _Inputs;
NeuronsInHidden = _NeuronsInHidden;
Outputs = _Outputs;
srand( (unsigned)time( NULL ) ); // seed the randomizer
W.resize(2); // setup weights
W[0].resize(((Inputs+1) * NeuronsInHidden), (float)((rand()%2000)-1000)/1000); // hidden layer
W[1].resize(((NeuronsInHidden+1) * Outputs), (float)((rand()%2000)-1000)/1000); // output layer
X.resize(3);
X[0].resize(Inputs+1, 0);
X[1].resize(NeuronsInHidden+1, 0);
X[2].resize(Outputs, 0);
}
NeuralNet::~NeuralNet() {
}
float NeuralNet::w(int l, int f, int n) { // f = 0 is bias weight
if(l == 0) // hidden layer
return W[0][((Inputs+1) * n) + f];
if(l == 1) // output layer
return W[1][((NeuronsInHidden+1) * n) + f];
else if(l != 0 && l != 1) {
cout << "Error: Bad layer number: " << l << endl;
return 0;
}
}
void NeuralNet::SetW(int l, int f, int n, float NewWeight) {
if(l == 0) // hidden layer
W[0][((Inputs+1) * n) + f] = NewWeight;
if(l == 1) // output layer
W[1][((NeuronsInHidden+1) * n) + f] = NewWeight;
else if(l != 0 && l != 1) {
cout << "Error: Bad layer number: " << l << endl;
return;
}
}
float NeuralNet::x(int l, int n) { // n = 0 is bias (1)
return X[l][n];
}
void NeuralNet::Train(float i1, float i2, float d) {
// first, process so we have the correct values stored inside the neural net
Process(i1, i2);
vector<float> HiddenDelta;
HiddenDelta.resize(NeuronsInHidden);
vector<float> OutputDelta;
OutputDelta.resize(Outputs);
// output layer delta
// d3(1) = x3(1)(1 - x3(1))(d - x3(1))
for(int n = 0; n < Outputs; n++) {
OutputDelta[n] = x(2,n) * (1 - x(2,n)) * (d - x(2,n));
//cout << "OutputDelta["<<n<<"] = " << x(2,n) << " * " << (1 - x(2,n)) << " * " << (d - x(2,n)) << endl;
//cout << OutputDelta[n] << endl;
}
// hidden layer delta
// formula: d2(1) = x2(1)(1 - x2(1))w3(1,1)d3(1)
for(int n = 0; n < NeuronsInHidden; n++) {
HiddenDelta[n] = x(1,n+1) * (1 - x(1,n+1)) * w(1,n+1,0) * OutputDelta[0];
//cout << "HiddenDelta["<<n<<"] = " << x(1,n+1) <<" * " << (1 - x(1,n+1)) <<" * " << w(1,n+1,0) << " * " << OutputDelta[0] << endl;
//cout << HiddenDelta[n] << endl;
}
// deltas calculated, now alter the weights
// formula: w2(0,1) = h*x1(0)*d2(1)
for(int n = 0; n < Outputs; n++) {
for(int i = 0; i < NeuronsInHidden+1; i++) {
SetW(1,i,n, w(1,i,n)+(LEARN_RATE * x(1,i) * OutputDelta[0]));
//cout << w(1,i,n)+(LEARN_RATE * x(1,i) * OutputDelta[0]) << endl;
}
}
for(int n = 0; n < NeuronsInHidden; n++) {
for(int i = 0; i < Inputs+1; i++) {
SetW(0,i,n, w(0,i,n)+(LEARN_RATE * x(0,i) * HiddenDelta[n]));
//cout << w(0,i,n)+(LEARN_RATE * x(0,i) * HiddenDelta[n]) << endl;
}
}
//cout << "--------\n";
}
float NeuralNet::Process(float i1, float i2) {
// store biases
X[0][0] = 1;
X[1][0] = 1;
// temp inputs
X[0][1] = 0;
X[0][2] = 0;
// sort out the hidden layers outputs
for(int n = 1; n < NeuronsInHidden+1; n++) { // loop through hiddens
for(int i = 0; i < Inputs+1; i++) // loop through inputs
X[1][n] += x(0, i) * w(0, i, n-1);
X[1][n] = Sigmoid(X[1][n]);
//cout << X[1][n] << endl;
}
// output neuron
for(int i = 0; i < NeuronsInHidden+1; i++)
X[2][0] += x(1, i) * w(1, i, n);
X[2][0] = Sigmoid(X[2][0]);
// --- Calculation done ---
return X[2][0];
}
And heres how I train it in main, the logical operation AND:
#include <iostream>
#include <conio.h>
#include "NeuralNet.h"
int main() {
NeuralNet X(2, 2, 1);
// Train
for(int a = 0; a < 5000; ++a) {
X.Train(0, 0, 0);
X.Train(1, 0, 0);
X.Train(0, 1, 0);
X.Train(1, 1, 1);
}
// Output what weve learned
cout << endl << X.Process(0, 0);
cout << endl << X.Process(1, 0);
cout << endl << X.Process(0, 1);
cout << endl << X.Process(1, 1);
getch();
return 1;
}
It always outputs the same value no matter what the inputs are. I cant find what Im doing wrong and I got that bad feeling Ive tried absolutely everything. :P
Any help cracking this one is greatly appreciated! [smile]
