jsat.classifiers.neuralnetwork.regularizers

Interface WeightRegularizer

All Superinterfaces:

java.io.Serializable

All Known Implementing Classes:

Max2NormRegularizer

public interface WeightRegularizer
extends java.io.Serializable

This interface defines the contract for applying a regularization scheme to the weight and bias values of a laying in a neural network.

Method Summary

Modifier and Type	Method and Description
void	applyRegularization(Matrix W, Vec b) Applies regularization to one matrix, where the rows of the matrix correspond tot he weights associated to one neuron's input.
void	applyRegularization(Matrix W, Vec b, java.util.concurrent.ExecutorService ex) Applies regularization to one matrix, where the rows of the matrix correspond tot he weights associated to one neuron's input.
double	applyRegularizationToRow(Vec w, double b) Applies the regularization to one row of the weight matrix, where the row corresponds to the weights into one neuron.
WeightRegularizer	clone()

Method Detail

applyRegularization

void applyRegularization(Matrix W,
                         Vec b)

Applies regularization to one matrix, where the rows of the matrix correspond tot he weights associated to one neuron's input. The vector of bias terms must then have the same length as the number of rows in the given matrix.

Parameters:

W - the matrix to apply regularization to

b - the vector of bias terms to apply regularization to

applyRegularization

void applyRegularization(Matrix W,
                         Vec b,
                         java.util.concurrent.ExecutorService ex)

Applies regularization to one matrix, where the rows of the matrix correspond tot he weights associated to one neuron's input. The vector of bias terms must then have the same length as the number of rows in the given matrix.

Parameters:

W - the matrix to apply regularization to

b - the vector of bias terms to apply regularization to

ex - the source of threads for parallel computation

applyRegularizationToRow

double applyRegularizationToRow(Vec w,
                                double b)

Applies the regularization to one row of the weight matrix, where the row corresponds to the weights into one neuron.

Parameters:

w - the weight row to be altered depending on the regularization method

b - the original bias input to this row

Returns:

the new bias value, or the same value if no change in the bias has occurred

clone

WeightRegularizer clone()