Code for retraining of ANN gives always the same results (MSE)

1 次查看（过去 30 天）

显示更早的评论

Léon 2011-9-25

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/16697-code-for-retraining-of-ann-gives-always-the-same-results-mse

在 MATLAB Online 中打开

I want to write a small loop to estimate the average performance of each network configuration (that I run n times), but unfortunately I get the same MSE values each time I run the code. Can somebody have a look?

net = init(net);
net = trainlm(net,inputs,targets);
P_train = [P_train; perform(net,trainTargets,outputs)]
P_val = [P_val; perform(net,valTargets,outputs)]
P_test = [P_test; perform(net,testTargets,outputs)]
average_perf = [mean(P_train);mean(P_val);mean(P_test)]

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Greg Heath 2011-10-13

This code makes no sense to me.

Please show more code with plenty of comments

that indicate what you are trying to do.

Greg

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Jonny 2011-10-12

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/16697-code-for-retraining-of-ann-gives-always-the-same-results-mse#answer_24392

Can you please show me a code if you write this loop?

Thanks :)

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

类别

AI and Statistics Deep Learning Toolbox Function Approximation, Clustering, and Control Function Approximation and Clustering

在 Help Center 和 File Exchange 中查找有关 Function Approximation and Clustering 的更多信息

标签

Community Treasure Hunt

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

Translated by