Trial-and-error or K-fold cross-validation

1 次查看（过去 30 天）
Hamza Ali
Hamza Ali 2017-9-30
评论： Hamza Ali 2017-10-1
Hello,
As researcher, i would like to ask for efficient algorithm to determine ANN's architecture (number of hidden neurons in one hidden layer),and i can not choose between Trial-and-Error and K-Fold Cross-validation. Indeed, most of researchers use in their articles K-Fold Cross-validation and i do not know why ? Thank you for you answer.

请先登录，再回答此问题。

采纳的回答

Greg Heath
Greg Heath 2017-10-1
If you search in both the NEWSGROUP and ANSWERS you will see zillions of examples of my two loop solution:
%Outer loop over number of hidden nodes, e.g.,
rng(0), j=0
for h = Hmin:dH:Hmax
j = j + 1
net = fitnet(h);
etc ...
%Inner loop over Ntrials sets of random initial weights
for i = 1:Ntrials
net = configure(net,x,t);
etc ...
Hope this helps.
Thank you for formally accepting my answer
Greg
  1 个评论
Hamza Ali
Hamza Ali 2017-10-1
Thank you Mr Greg. i will keep you informed of the results in order to discuss them.

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Nearest Neighbors 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