org.vizzini.ai.neuralnetwork
Interface IConnector

All Superinterfaces:
Cloneable
All Known Implementing Classes:
AbstractConnector, Connector

public interface IConnector
extends Cloneable

Defines methods required by neural network layer connectors.

Since:
v0.3
Version:
v0.3
Author:
Jeffrey M. Thompson

Method Summary
 void adjustWeights(double[][] deltas)
          Adjust the given layer's weights by adding the given deltas.
 Object clone()
          Return a clone of this instance.
 boolean equals(Object object)
          Return true if the given object is equal to this.
 void fillWeights(double value)
          Assign the given value to all weights of the neural network.
 ILayer getFromLayer()
          Return the from layer.
 ILayer getToLayer()
          Return the to layer.
 double getWeight(int i, int j)
          Return the weight for the given parameters.
 int getWeightCount()
          Return a count of the weights.
 double[] getWeights(int i)
          Return the weights for the given parameters.
 int hashCode()
          Return a hash code.
 void randomizeWeights()
          Assign random weights.
 void randomizeWeights(double range)
          Assign random weights.
 void setWeight(int i, int j, double weight)
          Set the weight for the given parameters.
 String toString()
          Return a string representation of this object.
 void zeroWeights()
          Assign zero weights.
 

Method Detail

adjustWeights

void adjustWeights(double[][] deltas)
Adjust the given layer's weights by adding the given deltas.

Parameters:
deltas - Weight deltas for the given layer.
Since:
v0.3

clone

Object clone()
Return a clone of this instance.

Since:
v0.3

equals

boolean equals(Object object)
Return true if the given object is equal to this.

Overrides:
equals in class Object
Parameters:
object - The object to compare equality against.
Returns:
Returns true if the objects are equal, otherwise false
Since:
v0.3

fillWeights

void fillWeights(double value)
Assign the given value to all weights of the neural network.

Since:
v0.3

getFromLayer

ILayer getFromLayer()
Return the from layer.

Since:
v0.3

getToLayer

ILayer getToLayer()
Return the to layer.

Since:
v0.3

getWeight

double getWeight(int i,
                 int j)
Return the weight for the given parameters.

Parameters:
i - From layer node index.
j - To layer node index.
Since:
v0.3

getWeightCount

int getWeightCount()
Return a count of the weights.

Since:
v0.3

getWeights

double[] getWeights(int i)
Return the weights for the given parameters.

Parameters:
i - From layer node index.
Since:
v0.3

hashCode

int hashCode()
Return a hash code.

Overrides:
hashCode in class Object
Since:
v0.3

randomizeWeights

void randomizeWeights()
Assign random weights.

Since:
v0.3

randomizeWeights

void randomizeWeights(double range)
Assign random weights.

Parameters:
range - ±Range of random weights around zero.
Since:
v0.3

setWeight

void setWeight(int i,
               int j,
               double weight)
Set the weight for the given parameters.

Parameters:
i - From layer node index.
j - To layer node index.
weight - New weight.
Since:
v0.3

toString

String toString()
Return a string representation of this object.

Overrides:
toString in class Object
Since:
v0.3

zeroWeights

void zeroWeights()
Assign zero weights.

Since:
v0.3


Copyright © 2007 Vizzini.org. All Rights Reserved. 2007.12.25.03.00.02