BP神經(jīng)網(wǎng)絡(luò)matlab實(shí)例(簡單而經(jīng)典)

1、精選優(yōu)質(zhì)文檔-傾情為你奉上p=p1't=t1' pn,minp,maxp,tn,mint,maxt=premnmx(p,t); %原始數(shù)據(jù)歸一化net=newff(minmax(pn),5,1,'tansig','purelin','traingdx'); %設(shè)置網(wǎng)絡(luò),建立相應(yīng)的BP網(wǎng)絡(luò)net.trainParam.show=2000; % 訓(xùn)練網(wǎng)絡(luò)net.trainParam.lr=0.01;net.trainParam.epochs=;net.trainParam.goal=1e-5;net,tr=train(net ,pn,

2、tn); %調(diào)用TRAINGDM算法訓(xùn)練BP網(wǎng)絡(luò)pnew=pnew1' pnewn=tramnmx(pnew,minp,maxp);anewn=sim(net,pnewn); %對BP網(wǎng)絡(luò)進(jìn)行仿真anew=postmnmx(anewn,mint,maxt); %還原數(shù)據(jù)y=anew'1、BP網(wǎng)絡(luò)構(gòu)建（1）生成BP網(wǎng)絡(luò)：由維的輸入樣本最小最大值構(gòu)成的維矩陣。：各層的神經(jīng)元個數(shù)。：各層的神經(jīng)元傳遞函數(shù)。：訓(xùn)練用函數(shù)的名稱。（2）網(wǎng)絡(luò)訓(xùn)練（3）網(wǎng)絡(luò)仿真'tansig','purelin','trainrp'BP網(wǎng)絡(luò)的訓(xùn)練函數(shù) 訓(xùn)練方法訓(xùn)

3、練函數(shù)梯度下降法traingd有動量的梯度下降法traingdm自適應(yīng)lr梯度下降法traingda自適應(yīng)lr動量梯度下降法traingdx彈性梯度下降法trainrpFletcher-Reeves共軛梯度法traincgfPloak-Ribiere共軛梯度法traincgpPowell-Beale共軛梯度法traincgb量化共軛梯度法trainscg擬牛頓算法trainbfg一步正割算法trainossLevenberg-MarquardttrainlmBP網(wǎng)絡(luò)訓(xùn)練參數(shù)訓(xùn)練參數(shù)參數(shù)介紹訓(xùn)練函數(shù)net.trainParam.epochs最大訓(xùn)練次數(shù)（缺省為10）traingd、traingd

4、m、traingda、traingdx、trainrp、traincgf、traincgp、traincgb、trainscg、trainbfg、trainoss、trainlmnet.trainParam.goal訓(xùn)練要求精度（缺省為0）traingd、traingdm、traingda、traingdx、trainrp、traincgf、traincgp、traincgb、trainscg、trainbfg、trainoss、trainlmnet.trainParam.lr學(xué)習(xí)率（缺省為0.01）traingd、traingdm、traingda、traingdx、trainrp、trai

5、ncgf、traincgp、traincgb、trainscg、trainbfg、trainoss、trainlmnet.trainParam.max_fail最大失敗次數(shù)（缺省為5）traingd、traingdm、traingda、traingdx、trainrp、traincgf、traincgp、traincgb、trainscg、trainbfg、trainoss、trainlmnet.trainParam.min_grad最小梯度要求（缺省為1e-10）traingd、traingdm、traingda、traingdx、trainrp、traincgf、traincgp、trai

6、ncgb、trainscg、trainbfg、trainoss、trainlmnet.trainParam.show顯示訓(xùn)練迭代過程（NaN表示不顯示，缺省為25）traingd、traingdm、traingda、traingdx、trainrp、traincgf、traincgp、traincgb、trainscg、trainbfg、trainoss、trainlmnet.trainParam.time最大訓(xùn)練時間（缺省為inf）traingd、traingdm、traingda、traingdx、trainrp、traincgf、traincgp、traincgb、trainscg、tr

7、ainbfg、trainoss、trainlmnet.trainParam.mc動量因子（缺省0.9）traingdm、traingdxnet.trainParam.lr_inc學(xué)習(xí)率lr增長比（缺省為1.05）traingda、traingdxnet.trainParam.lr_dec學(xué)習(xí)率lr下降比（缺省為0.7）traingda、traingdxnet.trainParam.max_perf_inc表現(xiàn)函數(shù)增加最大比（缺省為1.04）traingda、traingdxnet.trainParam.delt_inc權(quán)值變化增加量（缺省為1.2）trainrpnet.trainParam.d

8、elt_dec權(quán)值變化減小量（缺省為0.5）trainrpnet.trainParam.delt0初始權(quán)值變化（缺省為0.07）trainrpnet.trainParam.deltamax權(quán)值變化最大值（缺省為50.0）trainrpnet.trainParam.searchFcn一維線性搜索方法（缺省為srchcha）traincgf、traincgp、traincgb、trainbfg、trainossnet.trainParam.sigma因?yàn)槎吻髮?dǎo)對權(quán)值調(diào)整的影響參數(shù)（缺省值5.0e-5）trainscgnet.trainParam.lambdaHessian矩陣不確定性調(diào)節(jié)參數(shù)（缺

9、省為5.0e-7）trainscgnet.trainParam.men_reduc控制計算機(jī)內(nèi)存/速度的參量，內(nèi)存較大設(shè)為1，否則設(shè)為2（缺省為1）trainlmnet.trainParam.mu的初始值（缺省為0.001）trainlmnet.trainParam.mu_dec的減小率（缺省為0.1）trainlmnet.trainParam.mu_inc的增長率（缺省為10）trainlmnet.trainParam.mu_max的最大值（缺省為1e10）trainlm2、BP網(wǎng)絡(luò)舉例舉例1、%traingdclear;clc;P=-1 -1 2 2 4;0 5 0 5 7;T=-1 -1

10、 1 1 -1;%利用minmax函數(shù)求輸入樣本范圍net = newff(minmax(P),T,5,1,'tansig','purelin','trainrp');net.trainParam.show=50;%net.trainParam.lr=0.05;net.trainParam.epochs=300;net.trainParam.goal=1e-5;net,tr=train(net,P,T);net.iw1,1%隱層權(quán)值net.b1%隱層閾值net.lw2,1%輸出層權(quán)值net.b2%輸出層閾值sim(net,P)舉例2、利用三層BP

11、神經(jīng)網(wǎng)絡(luò)來完成非線性函數(shù)的逼近任務(wù)，其中隱層神經(jīng)元個數(shù)為五個。樣本數(shù)據(jù)：輸入X輸出D輸入X輸出D輸入X輸出D-1.0000-0.9602-0.30000.13360.40000.3072-0.9000-0.5770-0.2000-0.20130.50000.3960-0.8000-0.0729-0.1000-0.43440.60000.3449-0.70000.37710-0.50000.70000.1816-0.60000.64050.1000-0.39300.8000-0.3120-0.50000.66000.2000-0.16470.9000-0.2189-0.40000.46090.3

12、000-0.09881.0000-0.3201解：看到期望輸出的范圍是，所以利用雙極性Sigmoid函數(shù)作為轉(zhuǎn)移函數(shù)。程序如下：clear;clc;X=-1:0.1:1;D=-0.9602 -0.5770 -0.0729 0.3771 0.6405 0.6600 0.4609. 0.1336 -0.2013 -0.4344 -0.5000 -0.3930 -0.1647 -.0988. 0.3072 0.3960 0.3449 0.1816 -0.312 -0.2189 -0.3201;figure;plot(X,D,'*'); %繪制原始數(shù)據(jù)分布圖（附錄：1-1）net =

13、newff(-1 1,5 1,'tansig','tansig');net.trainParam.epochs = 1000; %訓(xùn)練的最大次數(shù)net.trainParam.goal = 0.005; %全局最小誤差net = train(net,X,D); O = sim(net,X); figure; plot(X,D,'*',X,O); %繪制訓(xùn)練后得到的結(jié)果和誤差曲線（附錄：1-2、1-3）V = net.iw1,1;%輸入層到中間層權(quán)值theta1 = net.b1;%中間層各神經(jīng)元閾值W = net.lw2,1;%中間層到輸出層權(quán)值t

14、heta2 = net.b2;%輸出層各神經(jīng)元閾值所得結(jié)果如下：輸入層到中間層的權(quán)值： 中間層各神經(jīng)元的閾值： 中間層到輸出層的權(quán)值： 輸出層各神經(jīng)元的閾值：舉例3、利用三層BP神經(jīng)網(wǎng)絡(luò)來完成非線性函數(shù)的逼近任務(wù)，其中隱層神經(jīng)元個數(shù)為五個。樣本數(shù)據(jù)：輸入X輸出D輸入X輸出D輸入X輸出D00448211539322621043371解：看到期望輸出的范圍超出，所以輸出層神經(jīng)元利用線性函數(shù)作為轉(zhuǎn)移函數(shù)。程序如下：clear; clc;X = 0 1 2 3 4 5 6 7 8 9 10;D = 0 1 2 3 4 3 2 1 2 3 4;figure;plot(X,D,'*');

15、%繪制原始數(shù)據(jù)分布圖net = newff(0 10,5 1,'tansig','purelin')net.trainParam.epochs = 100;net.trainParam.goal=0.005;net=train(net,X,D);O=sim(net,X);figure;plot(X,D,'*',X,O); %繪制訓(xùn)練后得到的結(jié)果和誤差曲線（附錄：2-2、2-3）V = net.iw1,1%輸入層到中間層權(quán)值theta1 = net.b1%中間層各神經(jīng)元閾值W = net.lw2,1%中間層到輸出層權(quán)值theta2 = net.b2

16、%輸出層各神經(jīng)元閾值所得結(jié)果如下：輸入層到中間層的權(quán)值：中間層各神經(jīng)元的閾值： 中間層到輸出層的權(quán)值： 輸出層各神經(jīng)元的閾值：問題：以下是上證指數(shù)2009年2月2日到3月27日的收盤價格，構(gòu)建一個三層BP神經(jīng)網(wǎng)絡(luò)，利用該組信號的6個過去值預(yù)測信號的將來值。日期價格日期價格2009/02/022011.6822009/03/022093.4522009/02/032060.8122009/03/032071.4322009/02/042107.7512009/03/042198.1122009/02/052098.0212009/03/052221.0822009/02/062181.24120

17、09/03/062193.0122009/02/092224.7112009/03/092118.7522009/02/102265.1612009/03/102158.5722009/02/112260.8222009/03/112139.0212009/02/122248.0922009/03/122133.8812009/02/132320.7922009/03/132128.8512009/02/162389.3922009/03/162153.2912009/02/172319.4422009/03/172218.3312009/02/182209.8622009/03/182223

18、.7312009/02/192227.1322009/03/192265.7612009/02/202261.4822009/03/202281.0912009/02/232305.7822009/03/232325.4812009/02/242200.6522009/03/242338.4212009/02/252206.5722009/03/252291.5512009/02/262121.2522009/03/262361.7012009/02/272082.8522009/03/272374.44load data3_1.txt;m,n=size( data3_1); tsx = da

19、ta3_1(1:m-1,1);tsx=tsx'ts = data3_1(2:m,1);ts=ts'TSX,TSXps=mapminmax(tsx,1,2);TS,TSps=mapminmax(ts,1,2);TSX=TSX' figure;plot(ts,'LineWidth',2);title('到杭旅游總?cè)藬?shù)(1999.01.01-2009.12.31)','FontSize',12);xlabel('統(tǒng)計年份(1990.12.19-2009.08.19)','FontSize',12);ylabel('歸一化后的總游客