基于Java实现的一层简单人工神经网络算法示例

import java.util.Arrays;
public class Data {
  double[] vector;
  int dimention;
  int type;
  public double[] getVector() {
    return vector;
  }
  public void setVector(double[] vector) {
    this.vector = vector;
  }
  public int getDimention() {
    return dimention;
  }
  public void setDimention(int dimention) {
    this.dimention = dimention;
  }
  public int getType() {
    return type;
  }
  public void setType(int type) {
    this.type = type;
  }
  public Data(double[] vector, int dimention, int type) {
    super();
    this.vector = vector;
    this.dimention = dimention;
    this.type = type;
  }
  public Data() {
  }
  @Override
  public String toString() {
    return "Data [vector=" + Arrays.toString(vector) + ", dimention=" + dimention + ", type=" + type + "]";
  }
}

package cn.edu.hbut.chenjie;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;
import org.jfree.chart.ChartFactory;
import org.jfree.chart.ChartFrame;
import org.jfree.chart.JFreeChart;
import org.jfree.data.xy.DefaultXYDataset;
import org.jfree.ui.RefineryUtilities;
public class ANN2 {
  private double eta;//学习率
  private int n_iter;//权重向量w[]训练次数
  private List exercise;//训练数据集
  private double w0 = 0;//阈值
  private double x0 = 1;//固定值
  private double[] weights;//权重向量，其长度为训练数据维度+1，在本例中数据为2维，故长度为3
  private int testSum = 0;//测试数据总数
  private int error = 0;//错误次数
  DefaultXYDataset xydataset = new DefaultXYDataset();
  /**
   * 向图表中增加同类型的数据
   * @param type 类型
   * @param a 所有数据的第一个分量
   * @param b 所有数据的第二个分量
   */
  public void add(String type,double[] a,double[] b)
  {
    double[][] data = new double[2][a.length];
    for(int i=0;i exercise = new ArrayList();//构造训练集
    //人工模拟1000条训练数据 ，分界线为x2=x1+0.5
    for(int i=0;i<1000000;i++)
    {
      Random rd = new Random();
      double x1 = rd.nextDouble();//随机产生一个分量
      double x2 = rd.nextDouble();//随机产生另一个分量
      double[] da = {x1,x2};//产生数据向量
      Data d = new Data(da, 2, x2 > x1+0.5 &＃63; 1 : -1);//构造数据
      exercise.add(d);//将训练数据加入训练集
    }
    int sum1 = 0;//记录类型1的训练记录数
    int sum2 = 0;//记录类型-1的训练记录数
    for(int i = 0; i  x1_+0.5 &＃63; 1 : -1);
      ann2.predict(test);//测试
    }
    System.out.println("总共测试" + ann2.testSum + "条数据,有" + ann2.error + "条错误,错误率:" + ann2.error * 1.0 /ann2.testSum * 100 + "%");
  }
  /**
   *
   * @param eta 学习率
   * @param n_iter 权重分量学习次数
   */
  public ANN2(double eta, int n_iter) {
    this.eta = eta;
    this.n_iter = n_iter;
  }
  /**
   * 输入训练集到人工神经网络
   * @param exercise
   */
  private void input(List exercise) {
    this.exercise = exercise;//保存训练集
    weights = new double[exercise.get(0).dimention + 1];//初始化权重向量，其长度为训练数据维度+1
    weights[0] = w0;//权重向量第一个分量为w0
    for(int i = 1; i =0)
      return 1;
    else
      return -1;
  }
  private void showWeigths()
  {
    for(double w : weights)
      System.out.println(w);
  }
  private void predict(Data data) {
    int type = CalculateResult(data);
    if(type == data.getType())
    {
      //System.out.println("预测正确");
    }
    else
    {
      //System.out.println("预测错误");
      error ++;
    }
    testSum ++;
  }
}

-0.22000000000000017
-0.4416843982815453
0.442444202054685
总共测试10000条数据,有17条错误,错误率:0.16999999999999998%