BP神经网络matlab源程序代码讲解 BP神经网络， MATLAB M文件源代码，跪求各位帮忙
bp\u795e\u7ecf\u7f51\u7edc\u9884\u6d4bmatlab\u6e90\u4ee3\u7801P=[1;2;3;4;5];%\u6708
P=[P/50]\uff1b
T=[2;3;4;5;6]\uff1b%\u6708\u8bad\u7ec3\u6837\u672c
T=[T/50]\uff1b
threshold=[0 1;0 1;0 1;0 1;0 1;0 1;0 1];
net=newff(threshold,[15,7],{'tansig','logsig'},'trainlm');
net.trainParam.epochs=2000;
net.trainParam.goal=0.001;
LP.lr=0.1;
net=train(net,P,T);
P_test=[6\u6708]';%6\u6708\u6570\u636e\u9884\u6d4b7\u6708
P_test=[P_test/50];
y=sim(net,P_test)
y=[y*50]
function [f1,f2]=forcast_neural(x1,y1,x2)
% \u6b64\u51fd\u6570\u7528\u795e\u7ecf\u7f51\u7edc\u8fdb\u884c\u9884\u6d4b
% x1: \u8bad\u7ec3\u8f93\u5165
% y1\uff1a \u8bad\u7ec3\u8f93\u51fa
% x2\uff1a \u6d4b\u8bd5\u8f93\u5165
% \u5c06\u8f93\u5165\u8f93\u51fa\u6570\u636e\u8fdb\u884c\u5f52\u4e00\u5316\u5904\u7406\uff1b
x1=x1';y1=y1';x2=x2';
warning('off')
[p,minp,maxp,t,mint,maxt]=premnmx(x1,y1);
x22=tramnmx(x2,minp,maxp);
% pr\u786e\u5b9a\u5404\u8f93\u5165\u53d8\u91cf\u7684\u6700\u5927\u6700\u5c0f\u503c\uff1b[8\uff0cr]\u5206\u522b\u8868\u793a\u5404\u5c42\u795e\u7ecf\u5143\u7684\u4e2a\u6570\uff0c8\u4ee3\u8868\u56e0\u5c42\uff0cr\u4ee3\u8868\u8f93\u51fa\u5c42\uff1b{}\u4e2d\u5b9a\u4e49\u4f20\u9012\u51fd\u6570\u7684\u7c7b\u578b
netw=newff(minmax(p),[8,1],{'tansig','purelin'},'trainlm');
%\u5c06\u7f51\u7edcnetw\u8d4b\u7ed9net
net=netw;
%\u5b9a\u4e49\u7f51\u7edc\u8bad\u7ec3\u8bef\u5dee
err=0.001;
net.trainParam.goal=err;
%\u5b9a\u4e49\u5b66\u4e60\u6548\u7387\uff0c\u5b66\u4e60\u6548\u7387\u975e\u5e38\u91cd\u8981\uff1a\u8fc7\u5927\uff0c\u8c03\u6574\u6b65\u4f10\u4e5f\u5927\uff0c\u5f71\u54cd\u8bad\u7ec3\u6548\u679c\uff1b\u592a\u5c0f\uff0c\u7b97\u6cd5\u6536\u655b\u7684\u65f6\u95f4\u5c31\u4f1a\u589e\u52a0
net.trainParam.lr=0.3;
%\u5b9a\u4e49\u6700\u5927\u8bad\u7ec3\u6b65\u6570
net.trainParam.epochs=2000;
%\u5b9a\u4e49\u663e\u793a\u7684\u95f4\u9694
net.trainParam.show=50;
%\u8bad\u7ec3\u795e\u7ecf\u7f51\u7edc
netw=train(net,p,t);
%\u5bf9\u8bad\u7ec3\u597d\u7684\u6837\u672c\u8fdb\u884c\u68c0\u9a8c
s1=sim(netw,p); %\u5bf9\u7f51\u7edc\u8fdb\u884c\u4eff\u771f\u68c0\u9a8c\uff0c\u5f97\u5230\u7f51\u7edc\u7684\u8f93\u51fa
%%\u8fdb\u884c\u9884\u6d4b
%\u8f93\u51fa
s2=sim(netw,x22);
%\u5c06\u5f52\u4e00\u5316\u7684\u6570\u636e\u8f6c\u6362\u4e3a\u539f\u59cb\u6570\u636e
[f1] = postmnmx(s1,mint,maxt);
[f2] = postmnmx(s2,mint,maxt);
net = newff(PR,[S1 S2...SNl],{TF1 TF2...TFNl},BTF,BLF,PF)
其中：PR —— R维输入元素的R×2阶最大最小值矩阵； Si —— 第i层神经元的个数，共N1层； TFi——第i层的转移函数，默认‘tansig’； BTF—— BP网络的训练函数，默认‘trainlm’; BLF—— BP权值/偏差学习函数，默认’learngdm’ PF ——性能函数，默认‘mse’；（误差）
e.g.
P = [0 1 2 3 4 5 6 7 8 9 10];T = [0 1 2 3 4 3 2 1 2 3 4];
net = newff([0 10],[5 1],{'tansig' 'purelin'});net.trainparam.show=50; %每次循环50次net.trainParam.epochs = 500; %最大循环500次
net.trainparam.goal=0.01; %期望目标误差最小值
net = train(net,P,T); %对网络进行反复训练
Y = sim(net,P)Figure % 打开另外一个图形窗口
plot(P,T,P,Y,'o')
绛旓細net.trainParam.epochs=1000; 鈥樻渶澶ц缁冩鏁帮紝鏍规嵁闇瑕佸彲鑷璋冭妭鈥檔et.trainParam.goal=0.01; 鈥樿宸檔et.trainParam.lr=0.01; 鈥樺涔犵巼鈥檔et=train(net,P,T); 鈥樿缁缃戠粶鈥檛est=[];鈥樺緟棰勬祴鏁版嵁杈撳叆鈥檕ut=sim(net,test); 鈥樹豢鐪熼娴嬧欐垜鐨勮繖涓绋嬪簭娌℃湁杩涜鍒濆鍖栵紝浣犺繕闇瑕佸厛灏嗘暟鎹繘琛...
绛旓細net.trainParam.lr=0.08;net.trainParam.goal=0.05;net.divideFcn = '';[net,tr]=train(net,inputn,outputn);%缃戠粶璁粌 缃戠粶棰勬祴杈撳嚭 an=sim(net,inputn_test);涓嶈繃鍙簡瑙ｈ緭鍏ラ娴嬭緭鍑猴紝杩欎簺杩樹笉澶燂紝杩樿鐪嬩綘鐨勮緭鍏ユ暟鎹殑閲忥紝鏉ョ‘瀹氶殣鍚眰锛岃繕闇瑕佺湅鏁版嵁鏄笉鏄綊涓鍖栵紝鎴戜笓闂ㄥ仛绁炵粡缃戠粶鐨勯娴...
绛旓細缁欎綘鎺ㄨ崘涓鏈功銆绁炵粡缃戠粶鐞嗚涓MATLAB7瀹炵幇銆嬶紝涓婇潰鏈塋M绠楁硶浠ュ強N澶氱殑浠ｇ爜
绛旓細浣跨敤绁炵粡缃戠粶宸ュ叿绠卞彲浠ラ潪甯哥畝渚垮湴瀹炵幇缃戠粶寤虹珛鍜岃缁冿紝瀹炰緥浠ｇ爜濡備笅锛BP绠楁硶function Out=bpnet(p,t,p_test)%p,t涓烘牱鏈渶瑕佹彁鍓嶇粍缁囧ソglobal S1net=newff(minmax(p),[S1,8],{'tansig','purelin'},'trainlm'); %trainlm璁粌鍑芥暟鏈鏈夋晥%net=newff(P,T,31,{'tansig','purelin'},'trainlm')...
绛旓細1,鎴戠敤鐨勬槸matlab R2008,涓鍒椾唬琛ㄤ竴涓牱鏈傚叾浠栫増鏈殑涓嶇煡閬 2锛宮atlab涓绁炵粡缃戠粶宸ュ叿绠卞氨宸茬粡寰堟柟渚夸簡锛岃皟鐢ㄥ嚱鏁板拰淇敼鍙傛暟灏卞彲浠ョ敤浜嗐3锛宯et_1.trainParam.lr浠ｈ〃瀛︿範閫熺巼锛宯et_1.trainParam.mc鍒欐槸鍔ㄩ噺绯绘暟銆傝嚦浜庡弬鏁扮殑纭畾锛岃鐪嬪叿浣撴儏鍐点
绛旓細缁欎綘涓涓垜鐨绋嬪簭锛屽鏋滆嚜宸卞仛涓嶄簡鍙互鑱旂郴鎴戯細1526208341 鍔ㄩ噺姊害涓嬮檷绠楁硶璁粌 BP 缃戠粶 璁粌鏍锋湰瀹氫箟濡備笅锛氳緭鍏ョ煝閲忎负 p =[-1 -2 3 1 -1 1 5 -3]鐩爣鐭㈤噺涓 t = [-1 -1 1 1]close all clear echo on clc NEWFF鈥斺旂敓鎴愪竴涓柊鐨勫墠鍚戠缁忕綉缁 TRAIN鈥斺斿 BP 绁炵粡缃戠粶杩涜璁粌...
绛旓細net = newff creates a new network with a dialog box.newff(PR,[S1 S2...SNl],{TF1 TF2...TFNl},BTF,BLF,PF) takes,PR -- R x 2 matrix of min and max values for R input elements 浣燩鏈9涓緭鍏ュ厓 R=9 matrix涓9X2 鎶妌et = newff([0,1],[10,9,9],{'tansig','...
绛旓細鍒涘缓涓涓墠棣堢綉缁 net=newff(minmax(x),[20,1],{'tansig','purelin'});浠跨湡鏈粡璁粌鐨勭綉缁渘et骞剁敾鍥 y1=sim(net,x);plot(x,y1,':');閲囩敤L-M浼樺寲绠楁硶 net.trainFcn='trainlm';璁剧疆璁粌绠楁硶 net.trainParam.epochs=500;net.trainParam.goal=10^(-6);璋冪敤鐩稿簲绠楁硶璁粌BP缃戠粶 [net,tr,yy]=...
绛旓細绀轰緥绋嬪簭瑙侀檮浠讹紝鍏朵负涓涓畝鍗曠殑鏃堕棿搴忓垪棰勬祴绠椾緥銆傚叾瀹炴墍鏈夌殑棰勬祴闂锛屾湰璐ㄩ兘鏄竴鏍风殑锛岄氳繃瀵规牱鏈殑瀛︿範锛屽皢缃戠粶璁粌鎴愪竴涓兘鍙嶆槧鏃堕棿搴忓垪鍐呴儴闈炵嚎鎬ц寰嬬殑绯荤粺锛屾渶缁堝簲鐢ㄤ簬棰勬祴銆BP锛圔ack Propagation锛绁炵粡缃戠粶鏄86骞寸敱Rumelhart鍜孧cCelland涓洪鐨勭瀛﹀灏忕粍鎻愬嚭锛屾槸涓绉嶆寜璇樊閫嗕紶鎾畻娉曡缁冪殑澶氬眰鍓嶉...
绛旓細clear all;close all;clc;p = [2056 2395 2600 2298 1634 1600 1837 1478 1900 2395 2600 2298 1634 1600 1873 1478 1900 1500 2600 2298 1634 1600 1873 1478 1900 1500 2046];t = [1873 1478 1900 1500 2046 1556];p = [ 2056 2395 2600 2298 1634 1600];--褰掍竴鍖栬緭鍏ヨ緭鍑-- 鏄犲皠鍒...
