java 印刷_Adaline网络识别印刷体数字0到9-java实现

packagecom.cgjr.com;importorg.neuroph.core.Layer;importorg.neuroph.core.NeuralNetwork;importorg.neuroph.nnet.comp.neuron.BiasNeuron;importorg.neuroph.nnet.learning.LMS;importorg.neuroph.util.ConnectionFactory;importorg.neuroph.util.LayerFactory;importorg.neuroph.util.NeuralNetworkFactory;importorg.neuroph.util.NeuralNetworkType;importorg.neuroph.util.NeuronProperties;importorg.neuroph.util.TransferFunctionType;public class Adaline extendsNeuralNetwork {/*** The class fingerprint that is set to indicate serialization compatibility

* with a previous version of the class.*/

private static final long serialVersionUID = 1L;/*** Creates new Adaline network with specified number of neurons in input

* layer

*

*@paraminputNeuronsCount

* number of neurons in input layer*/

public Adaline(int inputNeuronsCount, int outputNeuronsCount, doublelearnRate, TransferFunctionType transferFunction) {this.createNetwork(inputNeuronsCount, outputNeuronsCount, learnRate,transferFunction);

}/*** Creates adaline network architecture with specified number of input

* neurons

*

*@paraminputNeuronsCount

* number of neurons in input layer*/

private void createNetwork(int inputNeuronsCount, int outputNeuronsCount, doublelearnRate,

TransferFunctionType transferFunction) {//set network type code

this.setNetworkType(NeuralNetworkType.ADALINE);//create input layer neuron settings for this network

NeuronProperties inNeuronProperties = newNeuronProperties();

inNeuronProperties.setProperty("transferFunction", TransferFunctionType.LINEAR);//createLayer input layer with specified number of neurons

Layer inputLayer =LayerFactory.createLayer(inputNeuronsCount, inNeuronProperties);

inputLayer.addNeuron(new BiasNeuron()); //add bias neuron (always 1,//and it will act as bias input//for output neuron)

this.addLayer(inputLayer);//create output layer neuron settings for this network

NeuronProperties outNeuronProperties = newNeuronProperties();if (transferFunction ==TransferFunctionType.LINEAR) {

outNeuronProperties.setProperty("transferFunction", TransferFunctionType.LINEAR);

}else{

outNeuronProperties.setProperty("transferFunction", TransferFunctionType.RAMP);

outNeuronProperties.setProperty("transferFunction.slope", new Double(1));

outNeuronProperties.setProperty("transferFunction.yHigh", new Double(1));

outNeuronProperties.setProperty("transferFunction.xHigh", new Double(1));

outNeuronProperties.setProperty("transferFunction.yLow", new Double(-1));

outNeuronProperties.setProperty("transferFunction.xLow", new Double(-1));

}//createLayer output layer (only one neuron)

Layer outputLayer =LayerFactory.createLayer(outputNeuronsCount, outNeuronProperties);this.addLayer(outputLayer);//createLayer full conectivity between input and output layer

ConnectionFactory.fullConnect(inputLayer, outputLayer);//set input and output cells for network

NeuralNetworkFactory.setDefaultIO(this);//set LMS learning rule for this network

LMS l = newLMS();

l.setLearningRate(learnRate);this.setLearningRule(l);

}

}