how to calculate the error in Neural Network Back Propagation Network

14 次查看（过去 30 天）
ajith
ajith 2013-7-18
sir,
My doubt regards how to make the minum error rate =0.001
net = newff(input,target,10,{'tansig' 'purelin'},'trainlm');
nsch.trainparam.show=3;
nsch.trainparam.lr=0.1;
nsch.trainparam.mc=0.9;
nsch.trainparam.epochs=100;
nsch.trainparam.goal=1e-30;
net = train(net,input,target);
res=sim(net,input);

请先登录，再回答此问题。

采纳的回答

Greg Heath
Greg Heath 2013-7-22
Use as many defaults as possible
MSEgoal = 0.01*mean(var(target',1))
MinGrad = MSEgoal/100
net = newff(input,target);
net.trainParam.goal = MSEgoal;
net.trainParam.min_grad = MinGrad;
[ net tr output error ] = train(net, input, target);
For details, search ANSWERS using the search word msegoal
Hope this helps.
Greg
Thank you for formally accepting my answer
Greg

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by