org.jscience.computing.ai.neurocomputing
Class FFNHiddenLayer

java.lang.Object
  org.jscience.computing.ai.neurocomputing.FFNLayer
      org.jscience.computing.ai.neurocomputing.FFNHiddenLayer

public class FFNHiddenLayer
extends FFNLayer

This class implements a hidden layer for a feedforward network.

Field Summary

protected int

numUnits The number of units/nodes in this layer.

Fields inherited from class org.jscience.computing.ai.neurocomputing.FFNLayer

activate, connected, myNetwork, outputs, weights

Constructor Summary

FFNHiddenLayer(int units)
Creates a new instance of FFNHiddenLayer

Method Summary

int	getUnitCount() DOCUMENT ME!
void	setActivation(Activation activate) Set the activation function.

Methods inherited from class org.jscience.computing.ai.neurocomputing.FFNLayer

connectWith, getOutput, randomizeWeights, run, setNetwork, setWeights, setWeights

Methods inherited from class java.lang.Object

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

Field Detail

numUnits

protected int numUnits

The number of units/nodes in this layer.

Constructor Detail

FFNHiddenLayer

public FFNHiddenLayer(int units)

Creates a new instance of FFNHiddenLayer

Parameters:

units - the number of units in this layer.

Method Detail

setActivation

public void setActivation(Activation activate)

Set the activation function.

Parameters:

activate - the activation function.

getUnitCount

public int getUnitCount()

DOCUMENT ME!

Specified by:

getUnitCount in class FFNLayer

Returns:

DOCUMENT ME!