1.建立感知機

	private void creatNetwork(int inputNeuronsCount){
		
		//設定網路類別為感知機
		this.setNetworkType(NeuralNetworkType.PERCEPTRON);
		
		
		//建立輸入神經元，表示輸入的刺激
		NeuronProperties inputNeuron = new NeuronProperties();
		inputNeuron.setProperty("neuronType", InputNeuron.class);
		
		
		//由輸入神經元構成的底層
		Layer inputLayer = LayerFactory.createLayer(inputNeuronsCount, inputNeuron);
		this.addLayer(inputLayer);
		//在輸入層增加貝葉斯神經，表示神經元偏置
		inputLayer.addNeuron(new BiasNeuron());
		
		
		//設定傳遞函式為step()函式
		NeuronProperties outputProperties = new NeuronProperties();
		outputProperties.setProperty("transferFunction", TransferFunctionType.STEP);
		Layer outputLayer = LayerFactory.createLayer(1, outputProperties);
		this.addLayer(outputLayer);
		
		
		//將輸入層和輸出層進行全連線(輸入節點和每個神經元都兩兩連線)
		ConnectionFactory.fullConnect(inputLayer, outputLayer);
		NeuralNetworkFactory.setDefaultIO(this);
		Neuron n = outputLayer.getNeuronAt(0);
		
		System.out.println(n);
		
		//設定每個連線的權重，1和1是輸入節點到神經元的權值，-1.5是神經元的偏置
		n.getInputConnections()[0].getWeight().setValue(1);
		n.getInputConnections()[1].getWeight().setValue(1);
		n.getInputConnections()[2].getWeight().setValue(-1.5);
		
	}
 

2.使用感知機記憶邏輯與

public static void main(String[] args) {
		
		//建立學習資料集
		DataSet trainingSet = new DataSet(2,1);  //兩個輸入，一個輸出
		trainingSet.addRow(new DataSetRow(new double[] {0,0},new double[] {Double.NaN}));
		trainingSet.addRow(new DataSetRow(new double[] {0,1},new double[] {Double.NaN}));
		trainingSet.addRow(new DataSetRow(new double[] {1,0},new double[] {Double.NaN}));
		trainingSet.addRow(new DataSetRow(new double[] {1,1},new double[] {Double.NaN}));
		
		simpleDemo perceptron = new simpleDemo(2);
		
		for(DataSetRow row : trainingSet.getRows()){
			perceptron.setInput(row.getInput());
			perceptron.calculate();
			double[] networkOutput = perceptron.getOutput();
			System.out.println(Arrays.toString(row.getInput())+"="+Arrays.toString(networkOutput));
		}
		
		
	}
 

3.識別結果