org.neuroph.nnet
Class Adaline

java.lang.Object
  java.util.Observable
      org.neuroph.core.NeuralNetwork
          org.neuroph.nnet.Adaline

All Implemented Interfaces:

Serializable

public class Adaline
extends NeuralNetwork

Adaline neural network architecture with LMS learning rule. Uses bias input, bipolar inputs [-1, 1] and ramp transfer function It can be also created using binary inputs and linear transfer function, but that dont works for some problems.

Author:

Zoran Sevarac

See Also:

Serialized Form

Field Summary

Fields inherited from class org.neuroph.core.NeuralNetwork

output

Constructor Summary

Adaline(int inputNeuronsCount)
Creates new Adaline network with specified number of neurons in input layer

Method Summary

Methods inherited from class org.neuroph.core.NeuralNetwork

addLayer, addLayer, addPlugin, calculate, createConnection, getInputNeurons, getInputsCount, getLabel, getLayerAt, getLayers, getLayersCount, getLearningRule, getLearningThread, getNetworkType, getOutput, getOutputNeurons, getOutputsCount, getPlugin, indexOf, learn, learn, learnInNewThread, learnInNewThread, load, load, notifyChange, pauseLearning, randomizeWeights, randomizeWeights, randomizeWeights, randomizeWeights, removeLayer, removeLayerAt, removePlugin, reset, resumeLearning, save, setInput, setInputNeurons, setLabel, setLearningRule, setNetworkType, setOutputNeurons, stopLearning, toString

Methods inherited from class java.util.Observable

addObserver, clearChanged, countObservers, deleteObserver, deleteObservers, hasChanged, notifyObservers, notifyObservers, setChanged

Methods inherited from class java.lang.Object

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

Constructor Detail

Adaline

public Adaline(int inputNeuronsCount)

Creates new Adaline network with specified number of neurons in input layer

Parameters:

inputNeuronsCount - number of neurons in input layer