org.joone.engine

Class BiasedLinearLayer

java.lang.Object

org.joone.engine.Layer

org.joone.engine.SimpleLayer

org.joone.engine.BiasedLinearLayer

All Implemented Interfaces:

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

public class BiasedLinearLayer
extends SimpleLayer
implements LearnableLayer

This layer consists of linear neurons, i.e. neurons that sum up their inputs (actually this is done by the (full) synapse in Joone) along with their biases. In the learning process the biases are adjusted in an attempt to output a value closer to the desired output. This layer differs from LinearLayer in two ways: - This layer uses biases. These biases can/will also be adjusted in the learning process. - It has no scalar beta parameter.

Author:

Boris Jansen

See Also:

Serialized Form

Field Summary

Fields inherited from class org.joone.engine.Layer

bias, gradientInps, gradientOuts, inps, inputPatternListeners, learnable, learning, m_batch, monitor, myLearner, outputPatternListeners, outs, running, step, STOP_FLAG

Constructor Summary

Constructors

Constructor and Description
BiasedLinearLayer() Creates a new instance of BiasedLinearLayer
BiasedLinearLayer(java.lang.String anElemName) Creates a new instance of BiasedLinearLayer.

Method Summary

Methods

Modifier and Type	Method and Description
void	backward(double[] pattern) Reverse transfer function of the component.
void	forward(double[] pattern) Transfer function to recall a result on a trained net
double	getDefaultState() Return the default state of a node in this layer, such as 0 for a tanh or 0.5 for a sigmoid layer
double	getDerivative(int i) Similar to the backward message and used by RTRL
Learner	getLearner() Deprecated. - Used only for backward compatibility
double	getMaximumState() Return maximum value of a node in this layer
double	getMinimumState() Return minimum value of a node in this layer

Methods inherited from class org.joone.engine.SimpleLayer

getLearningRate, getLrate, getMomentum, setDimensions, setLrate, setMomentum, setMonitor

Methods inherited from class org.joone.engine.Layer

addInputSynapse, addNoise, addOutputSynapse, adjustSizeToFwdPattern, adjustSizeToRevPattern, check, checkInputEnabled, checkInputs, checkOutputs, copyInto, finalize, fireFwdGet, fireFwdPut, fireRevGet, fireRevPut, fwdRun, getAllInputs, getAllOutputs, getBias, getDimension, getLastGradientInps, getLastGradientOuts, getLastInputs, getLastOutputs, getLayerName, getMonitor, getRows, getThreadMonitor, hasStepCounter, init, initLearner, InspectableTitle, Inspections, isInputLayer, isOutputLayer, isRunning, join, randomize, randomizeBias, randomizeWeights, removeAllInputs, removeAllOutputs, removeInputSynapse, removeListener, removeOutputSynapse, resetInputListeners, revRun, run, setAllInputs, setAllOutputs, setBias, setConnDimensions, setInputDimension, setInputSynapses, setLastInputs, setLastOutputs, setLayerName, setOutputDimension, setOutputSynapses, setRows, start, stop, sumBackInput, sumInput, toString

Methods inherited from class java.lang.Object

clone, 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

BiasedLinearLayer

public BiasedLinearLayer()

Creates a new instance of BiasedLinearLayer

BiasedLinearLayer

public BiasedLinearLayer(java.lang.String anElemName)

Creates a new instance of BiasedLinearLayer.

Parameters:

The - name of the layer.

Method Detail

backward

public void backward(double[] pattern)

Description copied from class: Layer

Reverse transfer function of the component.

Overrides:

backward in class SimpleLayer

Parameters:

pattern - input pattern on which to apply the transfer function

getDerivative

public double getDerivative(int i)

Similar to the backward message and used by RTRL

Specified by:

getDerivative in class Layer

forward

public void forward(double[] pattern)

Description copied from class: Layer

Transfer function to recall a result on a trained net

Specified by:

forward in class Layer

Parameters:

pattern - input pattern to which to apply the rtransfer function

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()

getDefaultState

public double getDefaultState()

Description copied from class: Layer

Return the default state of a node in this layer, such as 0 for a tanh or 0.5 for a sigmoid layer

Specified by:

getDefaultState in class Layer

getMinimumState

public double getMinimumState()

Description copied from class: Layer

Return minimum value of a node in this layer

Specified by:

getMinimumState in class Layer

getMaximumState

public double getMaximumState()

Description copied from class: Layer

Return maximum value of a node in this layer

Specified by:

getMaximumState in class Layer