jsat.classifiers.neuralnetwork.activations

Interface ActivationLayer

All Superinterfaces:

java.io.Serializable

All Known Implementing Classes:

LinearLayer, ReLU, SigmoidLayer, SoftmaxLayer, SoftSignLayer, TanhLayer

public interface ActivationLayer
extends java.io.Serializable

This interface defines a type of activation layer for use in a Neural Network

Method Summary

Modifier and Type	Method and Description
void	activate(Matrix input, Matrix output, boolean rowMajor) Computes the activation function of this layer on the given input.
void	activate(Vec input, Vec output) Computes the activation function of this layer on the given input.
void	backprop(Matrix input, Matrix output, Matrix delta_partial, Matrix errout, boolean rowMajor) This method computes the backpropagated error to a given layer.
void	backprop(Vec input, Vec output, Vec delta_partial, Vec errout) This method computes the backpropagated error to a given layer.
ActivationLayer	clone()

Method Detail

activate

void activate(Vec input,
              Vec output)

Computes the activation function of this layer on the given input.

Parameters:

input - the raw input to compute the activation for

output - the location to store the activation in

activate

void activate(Matrix input,
              Matrix output,
              boolean rowMajor)

Computes the activation function of this layer on the given input.

Parameters:

input - the raw input to compute the activation for

output - the location to store the activation in

rowMajor - true if the information per input is stored in rows, false if the inputs were stored by column. This parameter does not indicate if the matrices themselves are backed by a row or column major implementation

backprop

void backprop(Vec input,
              Vec output,
              Vec delta_partial,
              Vec errout)

This method computes the backpropagated error to a given layer. Often denoted as δ^l = w^{l+1 T} δ^l+1 ⊗ ∂ f(x^l), where ∂ is the Hadamard product and ∂ f(x^l) is the derivative of this activation function on the input that was feed into this activation.
delta_partial and errout may point to the same vector object

Parameters:

input - the input to this layer that was feed in to be activated

output - the activation that was produced for this layer

delta_partial - the error assigned to this layer from the above layer, sans the hamard product with the derivative of the layer activation. Often denoted as w^{l+1 T} δ^l+1

errout - the delta value or error produced for this layer

backprop

void backprop(Matrix input,
              Matrix output,
              Matrix delta_partial,
              Matrix errout,
              boolean rowMajor)

This method computes the backpropagated error to a given layer. Often denoted as δ^l = w^{l+1 T} δ^l+1 ⊗ ∂ f(x^l), where ∂ is the Hadamard product and ∂ f(x^l) is the derivative of this activation function on the input that was feed into this activation.
delta_partial and errout may point to the same vector object

Parameters:

input - the input to this layer that was feed in to be activated

output - the activation that was produced for this layer

delta_partial - the error assigned to this layer from the above layer, sans the hamard product with the derivative of the layer activation. Often denoted as w^{l+1 T} δ^l+1

errout - the delta value or error produced for this layer

rowMajor - true if the information per input is stored in rows, false if the inputs were stored by column. This parameter does not indicate if the matrices themselves are backed by a row or column major implementation

clone

ActivationLayer clone()