public Dropout(Layer x, float prob)
{
InputLayers.Add(x);
InnerDimensionCalculation();
OuterDimensionCalculation();
Probability = prob;
}
public Subtract(Layer l1, Layer l2)
{
InputLayers.Add(l1);
InputLayers.Add(l2);
InnerDimensionCalculation();
OuterDimensionCalculation();
}
public DynamicRecurrent(Dimension[] outerDimensions, Dimension[] innerDimensions, Layer[] l, Func <Layer, List <Layer>, Index, Term> func)
{
foreach (var item in l)
{
InputLayers.Add(item);
}
this.OuterDimensions = outerDimensions;
this.InnerDimensions = innerDimensions;
this.F = func;
}
public Add(params Layer[] input)
{
terms = new Term[input.Length];
foreach (var item in input)
{
InputLayers.Add(item);
}
InnerDimensionCalculation();
OuterDimensionCalculation();
}
public Network(int inputSize, int hiddenSize, int outputSize, double?learnRate = null, double?momentum = null)
{
LearnRate = learnRate ?? .4;
Momentum = momentum ?? .9;
//InputLayer = new List<Neuron>();
HiddenLayer = new List <Neuron>();
OutputLayer = new List <Neuron>();
for (var i = 0; i < inputSize; i++)
{
InputLayers.Add(new Neuron());
}
for (var i = 0; i < hiddenSize; i++)
{
HiddenLayer.Add(new Neuron(InputLayers));
}
for (var i = 0; i < outputSize; i++)
{
OutputLayer.Add(new Neuron(HiddenLayer));
}
}
