org.joone.engine
Class SineLayer

java.lang.Object
  extended by org.joone.engine.Layer
      extended by org.joone.engine.SimpleLayer
          extended by org.joone.engine.SineLayer
All Implemented Interfaces:
java.io.Serializable, java.lang.Runnable, Learnable, LearnableLayer, NeuralLayer, Inspectable

public class SineLayer
extends SimpleLayer
implements LearnableLayer

The output of a sine layer neuron is the sum of the weighted input values, applied to a sine (sin(x)). Neurons with sine activation problems might be useful in problems with periodicity.

Author:
Boris Jansen
See Also:
parent, parent, implemented interface, 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
SineLayer()
          Creates a new instance of SineLayer
SineLayer(java.lang.String aName)
          Creates a new instance of SineLayer
 
Method Summary
 void backward(double[] aPattern)
          Reverse transfer function of the component.
protected  void forward(double[] aPattern)
          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
 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, getLearner, 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
getLearner, 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

SineLayer

public SineLayer()
Creates a new instance of SineLayer


SineLayer

public SineLayer(java.lang.String aName)
Creates a new instance of SineLayer

Parameters:
aName - The name of the layer
Method Detail

forward

protected void forward(double[] aPattern)
                throws JooneRuntimeException
Description copied from class: Layer
Transfer function to recall a result on a trained net

Specified by:
forward in class Layer
Parameters:
aPattern - input pattern to which to apply the rtransfer function
Throws:
JooneRuntimeException

backward

public void backward(double[] aPattern)
              throws JooneRuntimeException
Description copied from class: Layer
Reverse transfer function of the component.

Overrides:
backward in class SimpleLayer
Parameters:
aPattern - input pattern on which to apply the transfer function
Throws:
JooneRuntimeException

getDerivative

public double getDerivative(int i)
Similar to the backward message and used by RTRL

Specified by:
getDerivative in class Layer

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


Submit Feedback to pmarrone@users.sourceforge.net