C# Class NNX.Core.MultilayerPerceptron

Multilayer perceptron with the following features: * Hidden layer activation functions: tahn * Output layer activation function: softmax * Gradient calculation assumes optimization for min cross-entropy error.

Inheritance: INeuralNetwork

Show file Open project: ikhramts/NNX

Public Methods

Method	Description
CalculateGradients ( double inputs, double targets ) : double[][]	Calculates gradients of the error function (cross-entropy) with respect to weights.
FeedForward ( double inputs ) : FeedForwardResult	Activation functions: tanh for hidden nodes, softmax for output nodes.
MultilayerPerceptron ( int numInputs, int numOutputs, IList hiddenLayerSizes ) : System

Method Details

CalculateGradients() public method

Calculates gradients of the error function (cross-entropy) with respect to weights.

public CalculateGradients ( double inputs, double targets ) : double[][]
inputs	double
targets	double
return	double[][]

FeedForward() public method

Activation functions: tanh for hidden nodes, softmax for output nodes.

public FeedForward ( double inputs ) : FeedForwardResult
inputs	double
return	FeedForwardResult

MultilayerPerceptron() public method

public MultilayerPerceptron ( int numInputs, int numOutputs, IList hiddenLayerSizes ) : System
numInputs	int
numOutputs	int
hiddenLayerSizes	IList
return	System