bp神经网络详细步骤C实现.docxVIP

using System;using System.Collections.Generic;using System.Linq;using System.Text;using System;using System.IO;using System.Text;namespace BpANNet{/// summary/// BpNet的摘要说明。/// /summarypublic class BpNet{public intinNum;//输入节点数inthideNum;//隐层节点数public intoutNum;//输出层节点数public intsampleNum;//样本总数Random R;double [] x;//输入节点的输入数据double [] x1;//隐层节点的输出double [] x2;//输出节点的输出double [] o1;//隐层的输入double [] o2;//输出层的输入public double [,] w;//权值矩阵w，这是输入层与隐藏层之间的权值矩阵public double [,] v;//权值矩阵V，这是隐藏层与输出层之间的权值矩阵public double [,] dw;//权值矩阵wpublic double [,] dv;//权值矩阵Vpublic double rate;//学习率public double [] b1;//隐层阈值矩阵public double [] b2;//输出层阈值矩阵public double [] db1;//隐层阈值矩阵public double [] db2;//输出层阈值矩阵double [] pp;//隐藏层的误差double[] qq;//输出层的误差double [] yd;//输出层的教师数据，所谓教师数据就是实际数据而已！public double e;//均方误差double in_rate;//归一化比例系数//用于确定隐藏层的神经细胞数public intcomputeHideNum(intm,int n){double s=Math.Sqrt(0.43*m*n+0.12*n*n+2.54*m+0.77*n+0.35)+0.51;intss=Convert.ToInt32(s);return ((s-(double)ss)0.5) ? ss+1:ss;}public BpNet(double [,] p,double [,] t){// 构造函数逻辑R=new Random();this.inNum=p.GetLength(1);this.outNum=t.GetLength(1);this.hideNum=computeHideNum(inNum,outNum);//this.hideNum=18;this.sampleNum=p.GetLength(0);Console.WriteLine(输入节点数目： +inNum);Console.WriteLine(隐层节点数目：+hideNum);Console.WriteLine(输出层节点数目：+outNum);Console.ReadLine();//将这些矩阵规定好矩阵大小x=new double[inNum];x1=new double[hideNum];x2=new double[outNum];o1=new double[hideNum];o2=new double[outNum];w = new double[inNum, hideNum];//权值矩阵w，这是输入层与隐藏层之间的权值矩阵v=new double[hideNum,outNum];dw=new double[inNum,hideNum];dv=new double[hideNum,outNum];//阈值b1=new double[hideNum];b2=new double[outNum];db1=new double[hideNum];db2=new double[outNum];//误差pp = new double[hideNum];//隐藏层的误差qq = new double[outNum];//输出层的误差yd = new double[outNum];//输出层的教师数据//初始化wfor(int i=0;iinNum;i++){for(int j=0;jhideNum;j++){//NextDouble返回一个介于 0.0 和 1.0 之间的随机数。w[i,j]=(R.NextDouble()*2-1.0)/2;}}//初始化vfor(int i=0;ihideNum;i++){for(int j=0;joutNum;j++){v[i,j]=(R.NextDouble(