Class Synapse

java.lang.Object
  Synapse

Direct Known Subclasses:

ContextSynapse

public class Synapse

extends Object

The Synapse class is used to connect Neurons together. Synapses are created with adjustable random weights.

Author:

Raymond McBride

See Also:

ContextSynapse

Constructor Summary

Synapse(Neuron inputNeuron, Neuron outputNeuron)
This constructor for the Synapse connects two Neurons together, and sets it's weight to a random value

Method Summary

void	adjustWeight() Adjusts the weight
void	calculateWeightChange(double learningRate, double momentum, double errorTerm) Calculates the weight change
void	calculateWeightChange(double learningRate, double momentum, double errorTerm, int delays) Calculates the average weight change for use with time delays
double	getWeight() Gets the Synapse weight
protected void	setWeight(int newWeight) Sets the Synapse weight
void	transferValue() Transfers a weighted value from the input Neuron to the output Neuron

Methods inherited from class java.lang.Object

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

Constructor Detail

Synapse

public Synapse(Neuron inputNeuron,
               Neuron outputNeuron)

This constructor for the Synapse connects two Neurons together, and sets it's weight to a random value

Parameters:

inputNeuron - The input Neuron

outputNeuron - The output Neuron

Method Detail

getWeight

public double getWeight()

Gets the Synapse weight

Returns:

The weight

setWeight

protected void setWeight(int newWeight)

Sets the Synapse weight

Parameters:

newWeight - The new weight

calculateWeightChange

public void calculateWeightChange(double learningRate,
                                  double momentum,
                                  double errorTerm)

Calculates the weight change

calculateWeightChange

public void calculateWeightChange(double learningRate,
                                  double momentum,
                                  double errorTerm,
                                  int delays)

Calculates the average weight change for use with time delays

adjustWeight

public void adjustWeight()

Adjusts the weight

transferValue

public void transferValue()

Transfers a weighted value from the input Neuron to the output Neuron