org.joone.engine

Class SigmoidLayer

java.lang.Object

org.joone.engine.Layer

org.joone.engine.SimpleLayer

org.joone.engine.SigmoidLayer

All Implemented Interfaces:

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

public class SigmoidLayer
extends SimpleLayer
implements LearnableLayer

The output of a sigmoid layer neuron is the sum of the weighted input values, applied to a sigmoid function. This function is expressed mathematically as: y = 1 / (1 + e^-x) This has the effect of smoothly limiting the output within the range 0 and 1

See Also:

parent, parent, implemented interface, Serialized Form

Field Summary

Fields inherited from class org.joone.engine.Layer

STOP_FLAG

Constructor Summary

Constructors

Constructor and Description
SigmoidLayer() The constructor
SigmoidLayer(java.lang.String ElemName) The constructor

Method Summary

Modifier and Type	Method and Description
void	backward(double[] pattern) Reverse transfer function of the component.
void	forward(double[] pattern) This method accepts an array of values in input and forwards it according to the Sigmoid propagation pattern.
double	getFlatSpotConstant() Gets the flat spot constant.
Learner	getLearner() Deprecated. - Used only for backward compatibility
void	setFlatSpotConstant(double aConstant) Sets the constant to overcome the flat spot problem.

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, getMonitor, getRows, hasStepCounter, init, initLearner, InspectableTitle, Inspections, 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

Methods inherited from interface org.joone.engine.Learnable

getMonitor, initLearner

Methods inherited from interface org.joone.engine.NeuralLayer

addInputSynapse, addNoise, addOutputSynapse, check, copyInto, getAllInputs, getAllOutputs, getBias, getLayerName, getMonitor, getRows, isRunning, removeAllInputs, removeAllOutputs, removeInputSynapse, removeOutputSynapse, setAllInputs, setAllOutputs, setBias, setLayerName, setMonitor, setRows, start

Constructor Detail

SigmoidLayer

public SigmoidLayer()

The constructor

SigmoidLayer

public SigmoidLayer(java.lang.String ElemName)

The constructor

Parameters:

ElemName - The name of the Layer

Method Detail

backward

public void backward(double[] pattern)
              throws JooneRuntimeException

Description copied from class: Layer

Reverse transfer function of the component.

Parameters:

pattern - input pattern on which to apply the transfer function

Throws:

JooneRuntimeException

forward

public void forward(double[] pattern)
             throws JooneRuntimeException

This method accepts an array of values in input and forwards it according to the Sigmoid propagation pattern.

Parameters:

pattern -

Throws:

JooneRuntimeException - This Exception is a wrapper Exception when an Exception is thrown while doing the maths.

See Also:

(double[])

getLearner

public Learner getLearner()

Deprecated. - Used only for backward compatibility

Description copied from class: Layer

Returns the appropriate Learner object for this class depending on the Monitor.learningMode property value

Specified by:

getLearner in interface Learnable

Overrides:

getLearner in class Layer

Returns:

the Learner object if applicable, otherwise null

See Also:

Learnable.getLearner()

setFlatSpotConstant

public void setFlatSpotConstant(double aConstant)

Sets the constant to overcome the flat spot problem. This problem is described in: S.E. Fahlman, "An emperical study of learning speed in backpropagation with good scaling properties," Dept. Comput. Sci. Carnegie Mellon Univ., Pittsburgh, PA, Tech. Rep., CMU-CS-88-162, 1988. Setting this constant to 0 (default value), the derivative of the sigmoid function is unchanged (normal function). An good value for this constant might be 0.1.

Parameters:

aConstant -

getFlatSpotConstant

public double getFlatSpotConstant()

Gets the flat spot constant.

Returns:

the flat spot constant.