org.joone.engine

Class SoftmaxLayer

java.lang.Object

org.joone.engine.Layer

org.joone.engine.SimpleLayer

org.joone.engine.LinearLayer

org.joone.engine.SoftmaxLayer

All Implemented Interfaces:

java.io.Serializable, java.lang.Runnable, Learnable, LearnableLayer, NeuralLayer, Inspectable

public class SoftmaxLayer
extends LinearLayer

The outputs of the Softmax layer must be interpreted as probabilities. The output of each node, in fact, ranges from 0 and 1, and the sum of all the nodes is always 1. Useful to implement the 1 of C classification network.

See Also:

Serialized Form

Field Summary

Fields inherited from class org.joone.engine.Layer

STOP_FLAG

Constructor Summary

Constructors

Constructor and Description
SoftmaxLayer() Creates a new instance of SoftmaxLayer

Method Summary

Modifier and Type	Method and Description
void	forward(double[] pattern) Transfer function to recall a result on a trained net

Methods inherited from class org.joone.engine.LinearLayer

backward, getBeta, Inspections, setBeta

Methods inherited from class org.joone.engine.SimpleLayer

getLearningRate, getLrate, getMomentum, setLrate, setMomentum, setMonitor

Methods inherited from class org.joone.engine.Layer

addInputSynapse, addNoise, addOutputSynapse, check, copyInto, finalize, fwdRun, getAllInputs, getAllOutputs, getBias, getDimension, getLastOutputs, getLayerName, getLearner, getMonitor, getRows, hasStepCounter, init, initLearner, InspectableTitle, isInputLayer, isOutputLayer, isRunning, join, randomize, removeAllInputs, removeAllOutputs, removeInputSynapse, removeOutputSynapse, revRun, run, setAllInputs, setAllOutputs, setBias, setInputSynapses, setLayerName, setOutputSynapses, setRows, start, stop, toString

Methods inherited from class java.lang.Object

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

Constructor Detail

SoftmaxLayer

public SoftmaxLayer()

Creates a new instance of SoftmaxLayer

Method Detail

forward

public void forward(double[] pattern)

Description copied from class: Layer

Transfer function to recall a result on a trained net

Overrides:

forward in class LinearLayer

Parameters:

pattern - input pattern to which to apply the rtransfer function