MATLAB神經(jīng)網(wǎng)絡(luò)之各函數(shù)介紹

三形clearall;[x,y]=meshgrid(-8:0.1:8);z=sinc(x);mesh(x,y,z);set(gcf,'color','w');

效果圖如下設(shè)置圖形窗口背景為白色修改z的值clearall;[x,y]=meshgrid(-10:0.3:10);r=sqrt(x.^2+y.^2)+eps;z=sin(r)./r;mesh(x,y,z)初化函數(shù)clearall;net=newp([0,1;-2,2],1);disp('3?ê??ˉ???°μ?è¨?μê?￡o')w1=net.iw{1,1}disp('3?ê??ˉ???°μ?·§?μ?a')b1=net.b{1}net.iw{1,1}=[5,6];disp('?￡?￡?￡è¨?μ?a')w2=net.iw{1,1}net.b{1}=7;disp('·§?μ?a')b2=net.b{1}net=init(net); 利用網(wǎng)絡(luò)初始化復(fù)原網(wǎng)絡(luò)權(quán)值和閥值w3=net.iw{1,1}b3=net.b{1}用init函與數(shù)>>cearl;ntnwp[,;22,);tues}F';t}=;e=n(t; 驗值閥值wne.w1,}=e.1}w=0.8116 0b=24>感知器popv坐別popc數(shù)知線clearall;p=[-0.5,-0.5,0.3,-0.1,-0.8;-0.5,0.5,-0.5,1.0,0.0];t=[1,1,0,0,0];plotpv(p,t); 繪制樣本節(jié)點net=newp([-40,1;-1,50],1);holdonlinehandles=plotpc(net.IW{1},net.b{1});net.adaptParam.passes=3;linehandle=plotpc(net.IW{1},net.b{1});fora=1:25;;endtitle('thekindofxiangliang')真數(shù)在mb了sim函進(jìn)：)q)個向絡(luò)已。clearall;formatcompactnet=newp([-2,2;-2,2],1);net.IW{1,1}=[-1,1];net.b{1}=[1];p1=[1;1];a1=sim(net,p1)p2=[1;-1];a2=sim(net,p2)p3={[1;1],[1;-1]};a3=sim(net,p3)得到a1=1a2=0a3=[] ]能數(shù)b神經(jīng)網(wǎng)絡(luò)工具箱提供了e函規(guī)則絡(luò)：)Dperf_dy=mae(dy,e,y,x,perf,fp)Dperf_dx=mae(dx,e,y,x,perf,fp)Info=mae(code)e誤（, ty絡(luò)略；x為所有fppf表prdy表示返回perf對y的導(dǎo)；e（）將根據(jù)coe值的不；息：當(dāng)ce示稱當(dāng)cs時，表稱當(dāng)s數(shù)感，誤差clearall;net=newp([-10,10],1);p=[-10,-5,0,5,10];t=[0,0,1,1,1];y=sim(net,p)e=t-yperf=mae(e)得到：y=1 1 1 1 1e=1 1 0 0 0prf=0.000練數(shù)：n重復(fù)的把一組輸入向量應(yīng)用到一個網(wǎng)絡(luò)上，每次都更新網(wǎng)絡(luò)，直到達(dá)到某種準(zhǔn)則。停止準(zhǔn)則的可習(xí)梯。：)t是r為錄ye誤f的入時態(tài)，f；tpt表是0；pi表示初始是0；ai表示是0；感，類clearall;p=[0,0,1,1;0,1,0,1];t=[0,1,1,1];net=newp(minmax(p),1);y=sim(net,p)net.trainParam.epochs=20;net=train(net,p,t);y=sim(net,p);err1=mae(y-t)plotpv(p,y)title('?òá?àà±e')得到：y=1 1 1 11=0t數(shù)該函數(shù)為學(xué)習(xí)自適時。：) 參數(shù)與n致個絡(luò)適練clearall;p1={-1,0,1,0,1,1,-1,0,-1,1,0,1};t1={-1,-1,1,1,1,2,0,-1,-1,0,1,1};net=linearlayer(