資源簡(jiǎn)介
這是神經(jīng)網(wǎng)絡(luò)里面結(jié)構(gòu)優(yōu)化里面重要的剪枝方法之一,靈敏度剪枝方法。-This is a neural network structure optimization inside one of the methods inside the major pruning, sensitivity pruning method
代碼片段和文件信息
function?main()%Skeletonization方法
AllDataNum=300;
TrainDataNum=100;%訓(xùn)練樣本數(shù)
TestDataNum=100;
%目標(biāo)函數(shù)時(shí)間序列計(jì)算
u=rands(1AllDataNum+10);
y=zeros(1AllDataNum+10);
for?i=2:AllDataNum+1
????numerator=16*u(i-1)+8*y(i-1);
????denominator=3+4*(i-1)^2+4*(i-1)^2;
????append=2/10*u(i-1)+2/10*y(i-1);
????y(i)=numerator/denominator+append;
end
%產(chǎn)生所有輸入輸出樣本對(duì)
AllDataIn=[];
AllDataOut=[];
for?i=4:AllDataNum+1
????NewIn=[u(i-1);y(i-1);u(i-2);y(i-2);y(i-3)];
????AllDataIn=[AllDataIn?NewIn];%所有樣本輸入
????AllDataOut=[AllDataOut?y(i)];%所有樣本輸出
end
TrainDataIn=AllDataIn(:1:TrainDataNum);%訓(xùn)練樣本輸入
TrainDataOut=AllDataOut(:1:TrainDataNum);%訓(xùn)練樣本輸出
TestDataIn=AllDataIn(:TrainDataNum+1:TrainDataNum+TestDataNum);%測(cè)試樣本輸入
TestDataOut=AllDataOut(:TrainDataNum+1:TrainDataNum+TestDataNum);%測(cè)試樣本輸
?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----
?????文件???????6479??2009-05-22?10:28??skeletonization.m
-----------?---------??----------?-----??----
?????????????????6479????????????????????1
評(píng)論
共有 條評(píng)論