作者：北郵小生-chaosju

1.入門書籍推薦： 人工神經網路教程-韓力群  北京郵電大學出版社

      寫演算法要了解演算法的原理，方能寫出好演算法，明白原理實現演算法 事半功倍

2.Joone

JOONE(Java Object Oriented Neural Network)是sourceforge.net上一個用java語言迅速開發神經網路的開源專案。JOONE支援很多的特性，比如多執行緒和分散式計算，這意味著可以JOONE可以利用多處理器或是多計算機來均衡附載。

JOONE主要有三個大的模組：

      joone-engine：joone的核心模組。
      joone-editor

文件，原始碼下載地址：http://www.codertodeveloper.com/docs/documentation.html

-----------學會讀一手的東西，直接看文件原始碼

3.XOR（異或）例項的實現

public class XOR_Test implements NeuralNetListener,Serializable {

	private static final long serialVersionUID = -3597853311948127352L;
	private FileInputSynapse inputStream = null;
	private NeuralNet nnet = null;
 

	public static void main(String args[]) {
		XOR_Test xor = new XOR_Test();

		xor.initNeuralNet();
	}

	protected void initNeuralNet() {

		// 三層：輸入層 ，隱層，輸出層
		// create the three layers (using the sigmoid transfer function for the
		// hidden and the output layers)
		LinearLayer input = new LinearLayer();
		SigmoidLayer hidden = new SigmoidLayer();
		SigmoidLayer output = new SigmoidLayer();

		// set their dimensions(神經元):
		// 設定每層神經元的個數
		input.setRows(2);
		hidden.setRows(3);
		output.setRows(1);

		// Now build the neural net connecting the layers by creating the two
		// synapses(突觸)
		// 三層需要兩個突觸對其進行連線,建立神經元
		FullSynapse synapse_IH = new FullSynapse(); /* Input -> Hidden conn. */
		FullSynapse synapse_HO = new FullSynapse(); /* Hidden -> Output conn. */

		// 連線操作
		// Next connect the input layer with the hidden layer:
		input.addOutputSynapse(synapse_IH);
		hidden.addInputSynapse(synapse_IH);
		// and then, the hidden layer with the output layer:
		hidden.addOutputSynapse(synapse_HO);
		output.addInputSynapse(synapse_HO);

		// need a NeuralNet object that will contain all the Layers of the
		// network
		// 建立一個網路來容納各層
		nnet = new NeuralNet();
		nnet.addLayer(input, NeuralNet.INPUT_LAYER);
		nnet.addLayer(hidden, NeuralNet.HIDDEN_LAYER);
		nnet.addLayer(output, NeuralNet.OUTPUT_LAYER);
		
		
		Monitor monitor = nnet.getMonitor();
		// 設定神經網路的學習率，
		monitor.setLearningRate(0.8);
		// 設定神經網路的動量 為 0.3 這兩個變數與步長有關
		monitor.setMomentum(0.3);
		monitor.addNeuralNetListener(this);
		
		
		
		// 輸入流
		inputStream = new FileInputSynapse();
		/* The first two columns contain the input values */
		inputStream.setAdvancedColumnSelector("1,2");
		/* This is the file that contains the input data */
		inputStream.setInputFile(new File("E:\\joone\\XOR.txt"));
		// Next add the input synapse to the first layer.
		input.addInputSynapse(inputStream);

	
		

		TeachingSynapse trainer = new TeachingSynapse();
		/*
		 * Setting of the file containing the desired responses, provided by a
		 * FileInputSynapse
		 */
		FileInputSynapse samples = new FileInputSynapse();
		samples.setInputFile(new File("e:\\joone\\XOR.txt"));
		/* The output values are on the third column of the file */
		samples.setAdvancedColumnSelector("3");
		trainer.setDesired(samples);
		
		
		output.addOutputSynapse(trainer);
		/* We attach the teacher to the network */
		nnet.setTeacher(trainer);
		
		monitor.setTrainingPatterns(4); /* # of rows in the input file */
		monitor.setTotCicles(100000); /* How many times the net must be trained*/
		
		monitor.setLearning(true); /* The net must be trained */
		nnet.go(); /* The network starts the training phase */

	}


	@Override
	public void netStarted(NeuralNetEvent e) {
		System.out.println("Training...");

	}

	@Override
	public void cicleTerminated(NeuralNetEvent e) {
		Monitor mon = (Monitor)e.getSource();
		long c = mon.getCurrentCicle();
		/* We want print the results every 100 epochs */
		if (c % 100 == 0)
		System.out.println(c + " epochs remaining - RMSE = " +
		mon.getGlobalError());

	}

	@Override
	public void netStopped(NeuralNetEvent e) {
		System.out.println("Training Stopped...");
		long mystr = System.currentTimeMillis(); // 初始化當前的系統時間
		System.out.println(mystr);

		saveNeuralNet("d://xor.snet"); // 儲存生成當前時間的myxor.snet神經網路
		test();

	}
    public void test(){
    	NeuralNet xorNNet = this.restoreNeuralNet("D://xor.snet");
    	if (xorNNet != null) {
    	// we get the output layer
    	Layer output = xorNNet.getOutputLayer();
    	// we create an output synapse
    	FileOutputSynapse fileOutput = new FileOutputSynapse();
    	fileOutput.setFileName("d://xor_out.txt");
    	// we attach the output synapse to the last layer of the NN
    	output.addOutputSynapse(fileOutput);
    	// we run the neural network only once (1 cycle) in recall mode
    	xorNNet.getMonitor().setTotCicles(1);
    	xorNNet.getMonitor().setLearning(false);
    	xorNNet.go();
    	}
    }
	@Override
	public void errorChanged(NeuralNetEvent e) {
		Monitor mon = (Monitor) e.getSource();// 得到監控層的資訊
		long c = mon.getCurrentCicle();
		if (c % 100 == 0)
		System.out.println("Cycle: "
				+ (mon.getTotCicles() - mon.getCurrentCicle()) + " RMSE:"
				+ mon.getGlobalError()); // 輸出 訓練的次數和 rmse 均方誤差

	}
	
	public void saveNeuralNet(String fileName) {
		try {
			FileOutputStream stream = new FileOutputStream(fileName);
			ObjectOutputStream out = new ObjectOutputStream(stream);
			out.writeObject(nnet);// 寫入nnet物件
			out.close();
		} catch (Exception excp) {
			excp.printStackTrace();
		}
	}
	
	NeuralNet restoreNeuralNet(String fileName) {
		NeuralNetLoader loader = new NeuralNetLoader(fileName);
		NeuralNet nnet = loader.getNeuralNet();
		return nnet;
		}
	@Override
	public void netStoppedError(NeuralNetEvent e, String error) {
		// TODO Auto-generated method stub

	}
}
 

程式的輸出結果：

0.0022572691083591304
0.9972511752900466
0.9972455081943005
0.0037839413733784474

和異或的結果一直，訓練的次數約多，結果越接近-------0.1