org.deeplearning4j.nn.activation

Class SoftMax

java.lang.Object

org.deeplearning4j.nn.activation.SoftMax

All Implemented Interfaces:

com.google.common.base.Function<org.jblas.DoubleMatrix,org.jblas.DoubleMatrix>, Serializable, ActivationFunction

public class SoftMax
extends Object
implements ActivationFunction

Softmax function

Author:

Adam Gibson

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
SoftMax()

Method Summary

Methods

Modifier and Type	Method and Description
org.jblas.DoubleMatrix	apply(org.jblas.DoubleMatrix input)
org.jblas.DoubleMatrix	applyDerivative(org.jblas.DoubleMatrix input) Applies the derivative of this function

Methods inherited from class java.lang.Object

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

Methods inherited from interface com.google.common.base.Function

equals

Constructor Detail

SoftMax

public SoftMax()

Method Detail

apply

public org.jblas.DoubleMatrix apply(org.jblas.DoubleMatrix input)

Specified by:

apply in interface com.google.common.base.Function<org.jblas.DoubleMatrix,org.jblas.DoubleMatrix>

applyDerivative

public org.jblas.DoubleMatrix applyDerivative(org.jblas.DoubleMatrix input)

Description copied from interface: ActivationFunction

Applies the derivative of this function

Specified by:

applyDerivative in interface ActivationFunction

Parameters:

input - the input to apply it to

Returns:

the derivative of this function applied to the input