org.vizzini.ai.neuralnetwork
Class FeedForwardNetwork

java.lang.Object
  org.vizzini.ai.neuralnetwork.AbstractNeuralNetwork
      org.vizzini.ai.neuralnetwork.FeedForwardNetwork

All Implemented Interfaces:

Serializable, Cloneable, INeuralNetwork

public class FeedForwardNetwork
extends AbstractNeuralNetwork

Provides a standard feed-forward neural network, consisting of an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer.

Since:

v0.3

Version:

v0.3

Author:

Jeffrey M. Thompson

See Also:

Serialized Form

Constructor Summary

FeedForwardNetwork(int inputCount, int hiddenCount, int outputCount)
Construct this object using the given parameters.

Method Summary

Methods inherited from class org.vizzini.ai.neuralnetwork.AbstractNeuralNetwork

addConnector, addLayer, adjustWeights, clone, configure, connectorIterator, equals, evaluate, fillWeights, getActivationFunction, getConfiguration, getConnector, getConnector, getConnector, getConnectorCount, getConnectors, getInputScaler, getLayer, getLayerCount, getLayers, getMaxOutputValueIndex, getNodeInput, getNodeOutput, getOutputLayer, getOutputLayerIndex, getOutputs, getOutputScaler, getWeight, getWeights, hashCode, indexOf, isConnected, isConnected, randomizeWeights, randomizeWeights, setActivationFunction, setActivationFunction, setConnectors, setInputs, setInputScaler, setLayers, setNodeInput, setOutputScaler, setWeight, store, toString, zeroWeights

Methods inherited from class java.lang.Object

finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

FeedForwardNetwork

public FeedForwardNetwork(int inputCount,
                          int hiddenCount,
                          int outputCount)

Construct this object using the given parameters.

Parameters:

inputCount - Input node count.

hiddenCount - Hidden node count.

outputCount - Output node count.