org.deeplearning4j.nn.activation

Interface ActivationFunction

All Superinterfaces:

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

All Known Implementing Classes:

HardTanh, Sigmoid, SoftMax, Tanh

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

An activation function for a hidden layer for neural networks

Author:

Adam Gibson

Method Summary

Methods

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

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

apply, equals

Method Detail

applyDerivative

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

Applies the derivative of this function

Parameters:

input - the input to apply it to

Returns:

the derivative of this function applied to the input