BP神经网络算法的C语言实现代码(共6页).doc

《BP神经网络算法的C语言实现代码(共6页).doc》由会员分享，可在线阅读，更多相关《BP神经网络算法的C语言实现代码(共6页).doc（6页珍藏版）》请在淘文阁 - 分享文档赚钱的网站上搜索。

1、精选优质文档-倾情为你奉上/BP神经网络算法,c语言版本/VS2010下，无语法错误，可直接运行/添加了简单注释/欢迎学习交流#include #include #include #include #define N_Out 2 /输出向量维数#define N_In 3/输入向量维数#define N_Sample 6 /样本数量/BP人工神经网络typedef struct int LayerNum;/中间层数量double vN_In50;/中间层权矩阵i,中间层节点最大数量为50double w50N_Out;/输出层权矩阵double StudyRate;/学习率double Acc

2、uracy;/精度控制参数int MaxLoop;/最大循环次数 BPNet;/Sigmoid函数double fnet(double net) return 1/(1+exp(-net);/初始化int InitBpNet(BPNet *BP);/训练BP网络，样本为x，理想输出为yint TrainBpNet(BPNet *BP, double xN_SampleN_In, int yN_SampleN_Out) ;/使用BP网络int UseBpNet(BPNet *BP);/主函数int main()/训练样本double xN_SampleN_In = 0.8,0.5,0, 0.9,

3、0.7,0.3,1,0.8,0.5,0,0.2,0.3,0.2,0.1,1.3,0.2,0.7,0.8; /理想输出int yN_SampleN_Out = 0,1,0,1,0,1,1,1,1,0,1,0; BPNet BP;InitBpNet(&BP); /初始化BP网络结构TrainBpNet(&BP, x, y); /训练BP神经网络UseBpNet(&BP); /测试BP神经网络return 1; /使用BP网络int UseBpNet(BPNet *BP) double InputN_In;double Out150; double Out2N_Out; /Out1为中间层输出,Ou

4、t2为输出层输出/持续执行，除非中断程序while (1) printf(请输入3个数：n);int i, j;for (i = 0; i N_In; i+)scanf_s(%f, &Inputi);double Tmp;for (i = 0; i (*BP).LayerNum; i+) Tmp = 0;for (j = 0; j N_In; j+)Tmp += Inputj * (*BP).vji;Out1i = fnet(Tmp);for (i = 0; i N_Out; i+) Tmp = 0;for (j = 0; j (*BP).LayerNum; j+)Tmp += Out1j *

5、 (*BP).wji;Out2i = fnet(Tmp);printf(结果： );for (i = 0; i N_Out; i+)printf(%.3f , Out2i);printf(n);return 1;/训练BP网络，样本为x，理想输出为yint TrainBpNet(BPNet *BP, double xN_SampleN_In, int yN_SampleN_Out) double f = (*BP).Accuracy; /精度控制参数double a = (*BP).StudyRate; /学习率int LayerNum = (*BP).LayerNum; /中间层节点数dou

6、ble vN_In50, w50N_Out; /权矩阵double ChgH50, ChgON_Out; /修改量矩阵double Out150, Out2N_Out; /中间层和输出层输出量int MaxLoop = (*BP).MaxLoop; /最大循环次数int i, j, k, n;double Tmp;for (i = 0; i N_In; i+)/ 复制结构体中的权矩阵 for (j = 0; j LayerNum; j+)vij = (*BP).vij;for (i = 0; i LayerNum; i+)for (j = 0; j f & n MaxLoop; n+) e =

7、 0;for (i= 0; i N_Sample; i+) /计算中间层输出向量for (k= 0; k LayerNum; k+) Tmp = 0;for (j = 0; j N_In; j+)Tmp = Tmp + xij * vjk; Out1k = fnet(Tmp);/计算输出层输出向量for (k = 0; k N_Out; k+) Tmp = 0;for (j = 0; j LayerNum; j+)Tmp = Tmp + Out1j * wjk;Out2k = fnet(Tmp);/计算输出层的权修改量 for (j = 0; j N_Out; j+) ChgOj = Out2

8、j * (1 - Out2j) * (yij - Out2j);/计算输出误差for (j = 0; j N_Out ; j+) e = e + (yij - Out2j) * (yij - Out2j);/计算中间层权修改量for (j = 0; j LayerNum; j+) Tmp = 0;for (k = 0; k N_Out; k+)Tmp = Tmp + wjk * ChgOk;ChgHj = Tmp * Out1j * (1 - Out1j);/修改输出层权矩阵for (j = 0; j LayerNum; j+) for (k = 0; k N_Out; k+)wjk = wj

9、k + a * Out1j * ChgOk; for (j = 0; j N_In; j+)for (k = 0; k LayerNum; k+)vjk = vjk + a * xij * ChgHk; if (n % 10 = 0)printf(误差 : %fn, e);printf(总共循环次数：%dn, n);printf(调整后的中间层权矩阵：n);for (i = 0; i N_In; i+) for (j = 0; j LayerNum; j+)printf(%f , vij); printf(n);printf(调整后的输出层权矩阵：n);for (i = 0; i LayerN

10、um; i+) for (j = 0; j N_Out; j+)printf(%f , wij); printf(n);/把结果复制回结构体 for (i = 0; i N_In; i+) for (j = 0; j LayerNum; j+)(*BP).vij = vij;for (i = 0; i LayerNum; i+)for (j = 0; j N_Out; j+)(*BP).wij = wij;printf(BP网络训练结束！n);return 1;/初始化int InitBpNet(BPNet *BP) printf(请输入中间层节点数，最大数为100：n); scanf_s(%

11、d, &(*BP).LayerNum);printf(请输入学习率：n);scanf_s(%lf, &(*BP).StudyRate); /(*BP).StudyRate为double型数据，所以必须是lfprintf(请输入精度控制参数：n);scanf_s(%lf, &(*BP).Accuracy);printf(请输入最大循环次数：n);scanf_s(%d, &(*BP).MaxLoop);int i, j;srand(unsigned)time(NULL);for (i = 0; i N_In; i+) for (j = 0; j (*BP).LayerNum; j+)(*BP).vij = rand() / (double)(RAND_MAX); for (i = 0; i (*BP).LayerNum; i+) for (j = 0; j N_Out; j+)(*BP).wij = rand() / (double)(RAND_MAX); return 1;专心-专注-专业