神经网络算法应用

《神经网络算法应用》由会员分享，可在线阅读，更多相关《神经网络算法应用（18页珍藏版）》请在金锄头文库上搜索。

1、神经网络算法应用神经网络算法应用using System;using System.IO;using System.Text;namespace BpANNet/ / BpNet 的摘要说明。/ public class BpNetstatic int err2 = 0;static int err3 = 0;static int err1 = 0;public int inNum;/输入节点数int hideNum;/隐层节点数public int outNum;/输出层节点数public int sampleNum;/样本总数Random R;double x;/输入节点的输入数据doub

2、le 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 wpublic double, v;/权值矩阵 Vpublic 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;/输出层

3、的误差double qq;/隐层的误差double yd;/输出层的教师数据public double e;/均方误差public int computeHideNum(int m, int n)double s = Math.Sqrt(m+n)+4;int ss = Convert.ToInt32(s);return 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 = compu

4、teHideNum(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);x = new doubleinNum;x1 = new doublehideNum;x2 = new doubleoutNum;o1 = new doublehideNum;o2 = new doubleoutNum

5、;w = new doubleinNum, hideNum;v = new doublehideNum, outNum;dw = new doubleinNum, hideNum;dv = new doublehideNum, outNum;b1 = new doublehideNum;b2 = new doubleoutNum;db1 = new doublehideNum;db2 = new doubleoutNum;pp = new doublehideNum;qq = new doubleoutNum;yd = new doubleoutNum;/初始化 wfor (int i = 0; i 0.01);Console.WriteLine(“study:0“, study);bp.train_test();