BP神經(jīng)網(wǎng)絡(luò)的設(shè)計(jì)實(shí)例(MATLAB編程)

BP神經(jīng)網(wǎng)絡(luò)的設(shè)計(jì)實(shí)例(MATLAB編程):例1 采用動(dòng)量梯度下降算法訓(xùn)練 BP 網(wǎng)絡(luò)。?
訓(xùn)練樣本定義如下：?
輸入矢量為?????
?p =[-1 -2 3? 1??
???? -1? 1 5 -3]?
目標(biāo)矢量為?? t = [-1 -1 1 1]?
解：本例的 MATLAB 程序如下：??

close all??
clear??
echo on??
clc??
% NEWFF——生成一個(gè)新的前向神經(jīng)網(wǎng)絡(luò)??
% TRAIN——對(duì) BP 神經(jīng)網(wǎng)絡(luò)進(jìn)行訓(xùn)練??
% SIM——對(duì) BP 神經(jīng)網(wǎng)絡(luò)進(jìn)行仿真??
pause?????????
%? 敲任意鍵開(kāi)始??
clc??
%? 定義訓(xùn)練樣本??
% P 為輸入矢量??
P=[-1,? -2,??? 3,??? 1;?????? -1,??? 1,??? 5,? -3];?
% T 為目標(biāo)矢量??
T=[-1, -1, 1, 1];??
pause;??
clc??
%? 創(chuàng)建一個(gè)新的前向神經(jīng)網(wǎng)絡(luò)??
net=newff(minmax(P),[3,1],{'tansig','purelin'},'traingdm')?
%? 當(dāng)前輸入層權(quán)值和閾值??
inputWeights=net.IW{1,1}??
inputbias=net.b{1}??
%? 當(dāng)前網(wǎng)絡(luò)層權(quán)值和閾值??
layerWeights=net.LW{2,1}??
layerbias=net.b{2}??
pause??
clc??
%? 設(shè)置訓(xùn)練參數(shù)??
net.trainParam.show = 50;??
net.trainParam.lr = 0.05;??
net.trainParam.mc = 0.9;??
net.trainParam.epochs = 1000;??
net.trainParam.goal = 1e-3;??
pause??
clc??
%? 調(diào)用 TRAINGDM 算法訓(xùn)練 BP 網(wǎng)絡(luò)??
[net,tr]=train(net,P,T);??
pause??
clc??
%? 對(duì) BP 網(wǎng)絡(luò)進(jìn)行仿真??
A = sim(net,P)??
%? 計(jì)算仿真誤差??
E = T - A??
MSE=mse(E)??
pause??