Package com.jml.neural_network.activations

Class Activations

java.lang.Object

com.jml.neural_network.activations.Activations

public abstract class Activations
extends Object

A class which contains methods for geting various pre-made activation functions for use in neural network layers.

Field Summary

Fields

Modifier and Type	Field	Description
static ActivationFunction	linear	A pre-defined instance of the linear activation function.
static ActivationFunction	relu	A pre-defined instance of the Relu (Rectified Linear Unit) activation function.
static ActivationFunction	sigmoid	The sigmoid activation function.
static ActivationFunction	tanh	A pre-defined instance of the hyperbolic tangent activation function.

Constructor Summary

Constructors

Constructor	Description
Activations()

Method Summary

Modifier and Type	Method	Description
static ActivationFunction	linear()	Creates and returns a new instacne of the linear activation function.
static ActivationFunction	relu()	Creates and returns a new relu activatoin function.
static ActivationFunction	sigmoid()	Creates and returns a new instance of the sigmoid activation function.
static ActivationFunction	softmax()	Creates and returns a new instance of the softmax activations function.
static ActivationFunction	tanh()	Creates and returns a new instance of the hyperbolic tangent activation function.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Details

sigmoid

public static final ActivationFunction sigmoid

The sigmoid activation function. f(x)=1/(1+exp(-x))

relu

public static final ActivationFunction relu

A pre-defined instance of the Relu (Rectified Linear Unit) activation function. f(x)=max(0, x)

linear

public static final ActivationFunction linear

A pre-defined instance of the linear activation function. f(x)=x.

tanh

public static final ActivationFunction tanh

A pre-defined instance of the hyperbolic tangent activation function. f(x) = tanh(x) = (ex - e-x) / (ex + e-x)

Constructor Details

Activations

public Activations()

Method Details

sigmoid

public static ActivationFunction sigmoid()

Creates and returns a new instance of the sigmoid activation function.

Returns:

The sigmoid activation function. f(x)=1/(1+exp(-x))

relu

public static ActivationFunction relu()

Creates and returns a new relu activatoin function.

Returns:

An instance of the Relu (Rectified Linear Unit) activation function. f(x)=max(0, x)

linear

public static ActivationFunction linear()

Creates and returns a new instacne of the linear activation function.

Returns:

An instance of the linear activation function. f(x)=x.

tanh

public static ActivationFunction tanh()

Creates and returns a new instance of the hyperbolic tangent activation function.

Returns:

An instance of the he hyperbolic tangent activation function
f(x) = tanh(x) = (ex - e-x) / (ex + e-x)

softmax

public static ActivationFunction softmax()

Creates and returns a new instance of the softmax activations function.

Returns:

The softmax activation function. f(x)_i = exp(x_i) / sum_j=1^m( exp(x_j) ) where x is a vector of length m and sum_j=1^m ( exp(x_j) ) = exp(x₁) + exp(x₂) + ... + exp(x_m)