//Forward Propagate this Neuron
public void ForwardPropag(vNeuron[,] nn)
{
if (this.layer != 0)
{
this.GetInputs(nn);
}
this.output = Enumerable.Repeat(0d, this.inputs[0].Count).ToList();
this.postActOutput = Enumerable.Repeat(0d, this.inputs[0].Count).ToList();
this.handedDownDelta = main.createNewMatrix(inputs[0].Count, inputs[0].Count);
for (int i = 0; i < this.inputs.Count; i++)
{
List <double> curInput = this.inputs[i];
List <List <double> > result = MyMath.matMulti(this.weights[i], MyMath.makeVertiColMat(curInput));
this.output = MyMath.transposeMat(MyMath.matAdd(MyMath.makeVertiColMat(this.output), result))[0];
}
if (this.actFunc == actFuncType.logistic)
{
for (int j = 0; j < this.output.Count; j++)
{
this.postActOutput[j] = MyMath.logisticFunc(this.output[j], beta[j]);
}
}
else if (this.actFunc == actFuncType.identity)
{
for (int j = 0; j < this.output.Count; j++)
{
this.postActOutput[j] = MyMath.identityFunc(this.output[j], beta[j]);
}
}
}
//Back Propagate for Hidden Neuron
public void BackPropag(mNeuron[,] net, double learnRate, double bLearnRate)
{
List <List <double> > fPrime = new List <List <double> >();
if (this.actFunc == actFuncType.logistic)
{
for (int i = 0; i < this.output.Count; i++)
{
fPrime.Add(new List <double>());
for (int j = 0; j < this.output[0].Count; j++)
{
fPrime[i].Add(MyMath.logisticPrimeFunc(this.output[i][j]));
}
}
}
else if (this.actFunc == actFuncType.identity)
{
for (int i = 0; i < this.output.Count; i++)
{
fPrime.Add(new List <double>());
for (int j = 0; j < this.output[0].Count; j++)
{
fPrime[i].Add(1d);
}
}
}
for (int i = 0; i < this.inputNeurons.Count; i++)
{
List <List <double> > error = MyMath.matMulti(MyMath.transposeMat(this.weights[i]), this.handedDownDelta);
List <List <double> > result = MyMath.pointwiseMatMulti(error, fPrime);
this.delta = result;
this.beta = MyMath.matSub(this.beta, MyMath.scalarProd(bLearnRate, this.delta));
int m = inputNeurons[i][0];
int n = inputNeurons[i][1];
net[m, n].handedDownDelta = MyMath.matAdd(net[m, n].handedDownDelta, this.delta);
List <List <double> > matrix = this.weights[i];
List <List <double> > gradient = MyMath.matMulti(this.delta, MyMath.transposeMat(this.inputs[i]));
this.newWeights.Add(MyMath.matSub(matrix, MyMath.scalarProd(learnRate, gradient)));
}
}
//Forward Propagate this Neuron
public void ForwardPropag(mNeuron[,] nn)
{
if (this.layer != 0)
{
this.GetInputs(nn);
}
this.output = main.createNewMatrix(this.inputs[0].Count, this.inputs[0][0].Count);
this.postActOutput = main.createNewMatrix(this.inputs[0].Count, this.inputs[0][0].Count);
this.handedDownDelta = main.createNewMatrix(this.inputs[0].Count, this.inputs[0][0].Count);
for (int i = 0; i < this.inputs.Count; i++)
{
List <List <double> > curInput = this.inputs[i];
List <List <double> > result = MyMath.matMulti(this.weights[i], curInput);
this.output = MyMath.matAdd(this.output, result);
}
if (this.actFunc == actFuncType.logistic)
{
for (int m = 0; m < output.Count; m++)
{
for (int n = 0; n < output[0].Count; n++)
{
this.postActOutput[m][n] = MyMath.logisticFunc(this.output[m][n], this.beta[m][n]);
}
}
}
else if (this.actFunc == actFuncType.identity)
{
for (int m = 0; m < output.Count; m++)
{
for (int n = 0; n < output[0].Count; n++)
{
this.postActOutput[m][n] = MyMath.identityFunc(this.output[m][n], this.beta[m][n]);
}
}
}
}
