Package com.jml.neural_network.activations

Interface ActivationFunction

All Known Implementing Classes:

Linear, Relu, Sigmoid, Softmax, Tanh

public interface ActivationFunction

An interface for activation functions.

Method Summary

Modifier and Type	Method	Description
linalg.Matrix	back(linalg.Matrix data)	Applies backward pass of the activation function to a matrix (i.e.
linalg.Matrix	forward(linalg.Matrix data)	Applies the forward pass of activation function to a matrix.
String	getName()	Gets the name of the activation function.

Method Details

forward

linalg.Matrix forward(linalg.Matrix data)

Applies the forward pass of activation function to a matrix.

Parameters:

data - The matrix to apply activation function to.

Returns:

The result of the element-wise activation function applied to the matrix.

back

linalg.Matrix back(linalg.Matrix data)

Applies backward pass of the activation function to a matrix (i.e. the derivative).

Parameters:

data - The matrix to apply the derivative of the activation function with respect to weights.

Returns:

The backward pass of the activation function for the data matrix.

getName

String getName()

Gets the name of the activation function.

Returns:

The name of the activation function as a String.