资源描述：
《bp神经网络各种不同算法程序》由会员上传分享，免费在线阅读，更多相关内容在应用文档-天天文库。
1、Matlab的BP神经网络各种不同算法程序1:一般模式的BP:clcP=[-1-122;0505];T=[-1-111];net=newff(minmax(P),[3,1],{'tansig','purelin'},'traingd');net.trainParam.show=50;net.trainParam.lr=0.05;net.trainParam.epochs=300;net.trainParam.goal=1e-5[nettr]=train(net,P,T);2：加入动量的BPclcP=[-1-122;0505];T=[-1-11
2、1];net=newff(minmax(P),[3,1],{'tansig','purelin'},'traingdm');net.trainParam.show=10000;net.trainParam.lr=0.05;net.trainParam.mc=0.9;net.trainParam.epochs=10000;net.trainParam.goal=1e-5*100[nettr]=train(net,P,T);3：自适应LR变步长：clcP=[-1-122;0505];T=[-1-111];net=newff(minmax(P),[
3、3,1],{'tansig','purelin'},'traingda');net.trainParam.show=10000;net.trainParam.lr=0.05;net.trainParam.lr_inc=1.05;net.trainParam.epochs=10000;net.trainParam.goal=1e-5*100[nettr]=train(net,P,T);4：弹性梯度法clcP=[-1-122;0505];T=[-1-111];net=newff(minmax(P),[3,1],{'tansig','purelin
4、'},'trainrp');net.trainParam.show=10000;net.trainParam.lr=0.05;net.trainParam.lr_inc=1.05;net.trainParam.epochs=10000;net.trainParam.goal=1e-5*100[nettr]=train(net,P,T);5：共轭梯度1clcP=[-1-122;0505];T=[-1-111];net=newff(minmax(P),[3,1],{'tansig','purelin'},'traincgf');net.train
5、Param.show=10000;net.trainParam.lr=0.05;net.trainParam.lr_inc=1.05;net.trainParam.epochs=10000;net.trainParam.goal=1e-5*100[nettr]=train(net,P,T);6：共轭梯度2clcP=[-1-122;0505];T=[-1-111];net=newff(minmax(P),[3,1],{'tansig','purelin'},'traincgp');net.trainParam.show=10000;net.tr
6、ainParam.lr=0.05;net.trainParam.lr_inc=1.05;net.trainParam.epochs=10000;net.trainParam.goal=1e-5*100[nettr]=train(net,P,T);7：共轭梯度3clcP=[-1-122;0505];T=[-1-111];net=newff(minmax(P),[3,1],{'tansig','purelin'},'traincgb');net.trainParam.show=10000;net.trainParam.lr=0.05;net.tr
7、ainParam.lr_inc=1.05;net.trainParam.epochs=10000;net.trainParam.goal=1e-5*100[nettr]=train(net,P,T);8：共轭梯度4clcP=[-1-122;0505];T=[-1-111];net=newff(minmax(P),[3,1],{'tansig','purelin'},'traincgb');net.trainParam.show=10000;net.trainParam.lr=0.05;net.trainParam.lr_inc=1.05;ne
8、t.trainParam.epochs=10000;net.trainParam.goal=1e-5*100[nettr]=train(net,P,T);9：拟牛顿
