Docjar: A Java Source and Docuemnt Enginecom.*    java.*    javax.*    org.*    all    new    plug-in

Quick Search    Search Deep

AI.NeuralNetworks
Class FeedForwardWeightedLayer  view FeedForwardWeightedLayer download FeedForwardWeightedLayer.java

java.lang.Object
  extended byAI.NeuralNetworks.FeedForwardLayer
      extended byAI.NeuralNetworks.FeedForwardWeightedLayer
Direct Known Subclasses:
FeedForwardWeightedTrainingLayer

public class FeedForwardWeightedLayer
extends FeedForwardLayer

This class is used to represent the inner and output layers of a multilayer feed forward neural network


Field Summary
private static float SEED_WIDTH
           
protected  float[][] weights
           
 
Fields inherited from class AI.NeuralNetworks.FeedForwardLayer
activation
 
Constructor Summary
FeedForwardWeightedLayer(FeedForwardWeightedLayer layer)
          creates a new insatnce of FeedForwardWeightedLayer
FeedForwardWeightedLayer(float[][] weights)
          creates a new insatnce of FeedForwardWeightedLayer
FeedForwardWeightedLayer(int size, int previousSize)
          creates a new insatnce of FeedForwardWeightedLayer
 
Method Summary
protected  float[][] getWeights()
           
 void runLayer(FeedForwardLayer previousLayer)
          Calculates the new activation values of this layer based on the previous layer
protected static float sigmoid(float x)
          returns the value of the sigmoid function 1/(1+exp(-x))
 java.lang.String toString()
          returns a String representation of the layer
 
Methods inherited from class AI.NeuralNetworks.FeedForwardLayer
getActivation, size
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Field Detail

weights

protected float[][] weights

SEED_WIDTH

private static float SEED_WIDTH
Constructor Detail

FeedForwardWeightedLayer

public FeedForwardWeightedLayer(int size,
                                int previousSize)
creates a new insatnce of FeedForwardWeightedLayer


FeedForwardWeightedLayer

public FeedForwardWeightedLayer(FeedForwardWeightedLayer layer)
creates a new insatnce of FeedForwardWeightedLayer


FeedForwardWeightedLayer

public FeedForwardWeightedLayer(float[][] weights)
creates a new insatnce of FeedForwardWeightedLayer

Method Detail

runLayer

public void runLayer(FeedForwardLayer previousLayer)
Calculates the new activation values of this layer based on the previous layer


sigmoid

protected static float sigmoid(float x)
returns the value of the sigmoid function 1/(1+exp(-x))


getWeights

protected float[][] getWeights()

toString

public java.lang.String toString()
returns a String representation of the layer

Overrides:
toString in class FeedForwardLayer