机器学习-11-BP神经网络-数据读取与基本结构

学习来源：日撸 Java 三百行（71-80天，BP 神经网络）_闵帆的博客-CSDN博客

BP神经网络（全连接神经网络）

传统的神经网络，只有输入层、隐藏层、输出层，其中隐藏层的层数根据需要而定。

主要分为两个步骤：1.前向预测；2.后向调整权重。

前向预测

神经网络只做一件事情：属性提取

例如：如果输出层有3个结点，表示类别，谁的输出值大，就判断未哪一类。

后向调整权重

使用梯度下降的方法对权值调整。（权值初始化为随机值）

激活函数

为了改变线性，采用激活函数。否则多层与一层等价。比如，一个为WX=Y，另一个为CX=B，DB=Y。则DC可由W代替。

sigmoid函数

tanh函数

 relu函数

 

代码：

package 日撸Java300行_71_80;

import java.io.FileReader;
import java.util.Arrays;
import java.util.Random;

import weka.core.Instances;

/**
 * General ANN. Two methods are abstract: forward and backPropagation.
 * 
 * @author Hui Xiao
 */
public abstract class GeneralAnn {

	/**
	 * The whole dataset.
	 */
	Instances dataset;

	/**
	 * Number of layers. It is counted according to nodes instead of edges.
	 */
	int numLayers;

	/**
	 * The number of nodes for each layer, e.g., [3, 4, 6, 2] means that there
	 * are 3 input nodes (conditional attributes), 2 hidden layers with 4 and 6
	 * nodes, respectively, and 2 class values (binary classification).
	 */
	int[] layerNumNodes;

	/**
	 * Momentum coefficient.
	 */
	public double mobp;

	/**
	 * Learning rate.
	 */
	public double learningRate;

	/**
	 * For random number generation.
	 */
	Random random = new Random();

	/**
	 ********************
	 * The first constructor.
	 * 
	 * @param paraFilename
	 *            The arff filename.
	 * @param paraLayerNumNodes
	 *            The number of nodes for each layer (may be different).
	 * @param paraLearningRate
	 *            Learning rate.
	 * @param paraMobp
	 *            Momentum coefficient.
	 ********************
	 */
	public GeneralAnn(String paraFilename, int[] paraLayerNumNodes, double paraLearningRate,
			double paraMobp) {
		// Step 1. Read data.
		try {
			FileReader tempReader = new FileReader(paraFilename);
			dataset = new Instances(tempReader);
			// The last attribute is the decision class.
			dataset.setClassIndex(dataset.numAttributes() - 1);
			tempReader.close();
		} catch (Exception ee) {
			System.out.println("Error occurred while trying to read \'" + paraFilename
					+ "\' in GeneralAnn constructor.\r\n" + ee);
			System.exit(0);
		} // Of try

		// Step 2. Accept parameters.
		layerNumNodes = paraLayerNumNodes;
		numLayers = layerNumNodes.length;
		// Adjust if necessary.
		layerNumNodes[0] = dataset.numAttributes() - 1;
		layerNumNodes[numLayers - 1] = dataset.numClasses();
		learningRate = paraLearningRate;
		mobp = paraMobp;	
	}//Of the first constructor	
	
	/**
	 ********************
	 * Forward prediction.
	 * 
	 * @param paraInput
	 *            The input data of one instance.
	 * @return The data at the output end.
	 ********************
	 */
	public abstract double[] forward(double[] paraInput);

	/**
	 ********************
	 * Back propagation.
	 * 
	 * @param paraTarget
	 *            For 3-class data, it is [0, 0, 1], [0, 1, 0] or [1, 0, 0].
	 *            
	 ********************
	 */
	public abstract void backPropagation(double[] paraTarget);

	/**
	 ********************
	 * Train using the dataset.
	 ********************
	 */
	public void train() {
		double[] tempInput = new double[dataset.numAttributes() - 1];
		double[] tempTarget = new double[dataset.numClasses()];
		for (int i = 0; i < dataset.numInstances(); i++) {
			// Fill the data.
			for (int j = 0; j < tempInput.length; j++) {
				tempInput[j] = dataset.instance(i).value(j);
			} // Of for j

			// Fill the class label.
			Arrays.fill(tempTarget, 0);
			tempTarget[(int) dataset.instance(i).classValue()] = 1;

			// Train with this instance.
			forward(tempInput);
			backPropagation(tempTarget);
		} // Of for i
	}// Of train

	/**
	 ********************
	 * Get the index corresponding to the max value of the array.
	 * 
	 * @return the index.
	 ********************
	 */
	public static int argmax(double[] paraArray) {
		int resultIndex = -1;
		double tempMax = -1e10;
		for (int i = 0; i < paraArray.length; i++) {
			if (tempMax < paraArray[i]) {
				tempMax = paraArray[i];
				resultIndex = i;
			} // Of if
		} // Of for i

		return resultIndex;
	}// Of argmax

	/**
	 ********************
	 * Test using the dataset.
	 * 
	 * @return The precision.
	 ********************
	 */
	public double test() {
		double[] tempInput = new double[dataset.numAttributes() - 1];

		double tempNumCorrect = 0;
		double[] tempPrediction;
		int tempPredictedClass = -1;

		for (int i = 0; i < dataset.numInstances(); i++) {
			// Fill the data.
			for (int j = 0; j < tempInput.length; j++) {
				tempInput[j] = dataset.instance(i).value(j);
			} // Of for j

			// Train with this instance.
			tempPrediction = forward(tempInput);
			//System.out.println("prediction: " + Arrays.toString(tempPrediction));
			tempPredictedClass = argmax(tempPrediction);
			if (tempPredictedClass == (int) dataset.instance(i).classValue()) {
				tempNumCorrect++;
			} // Of if
		} // Of for i

		System.out.println("Correct: " + tempNumCorrect + " out of " + dataset.numInstances());

		return tempNumCorrect / dataset.numInstances();
	}// Of test
}//Of class GeneralAnn