public HiddenLayer(uint numberOfNeurons, Layer previous)
: base(numberOfNeurons)
{
this.previousLayer = previous;
// default activation function is logsig
this.activationFunction = ActivationFunction.LogSig;
this.pointer = new ToActivationFunction(NMath.LogSig);
this.pDeriv = new ToActivationDerivative(NMath.DLogSig);
this.input = previous.GetOutputVector();
//
try
{
layerNeurons = new Neuron[numberOfNeurons];
//
for(int i=0; i<numberOfNeurons; i++)
{
layerNeurons[i] = new Neuron(previous.GetSize());
layerNeurons[i].SetInputVector(input);
}
//
}
catch(System.Exception exception)
{
Console.WriteLine("****EXCEPTION****\n {0} {1}", exception.Message);
previousLayer = null;
pointer = null;
layerNeurons = null;
}
}
//
public void FeedForward(ToActivationFunction pointer)
{
double neuronInput = 0.0;
//
for(int i=0; i<weights.Length; i++)
{
neuronInput += input[i]*weights[i];
}
//
// add bias
neuronInput += bias;
// pass neuron input to activation function and get output
output = pointer(neuronInput);
}
//
public void SetActivationFunction(ActivationFunction af)
{
this.activationFunction = af;
//
switch(af)
{
case ActivationFunction.LogSig:
this.pointer = new ToActivationFunction(NMath.LogSig);
this.pDeriv = new ToActivationDerivative(NMath.DLogSig);
break;
case ActivationFunction.TanSig:
this.pointer = new ToActivationFunction(NMath.TanSig);
this.pDeriv = new ToActivationDerivative(NMath.DTanSig);
break;
case ActivationFunction.Linear:
this.pointer = new ToActivationFunction(NMath.Linear);
this.pDeriv = new ToActivationDerivative(NMath.DLinear);
break;
default:
break;
}
}
