Is the validation data in a Neural Network to fit a function using Bayesian Regularization irrelevant?

2017 7 22
2 个回答
回答已采纳
更新时间：2017 7 23
8 次查看（30 天）

1 个投票

I'm using Bayesian Regularization to train a Neural Network and I notice the performance graph doesn't show the validation data. The algorithm doesn't use the validation data, in my understanding. Is it possible/viable to set to zero the percentage when training with Bayesian Regularization ?

请先登录，再回答此问题。

 采纳的回答

Greg Heath
Greg Heath 2017-7-23

1 个投票

That is a MATLAB design flaw. The older versions of TRAINBR do not allow a val subset. I have complained several times about that, especially since recent publications have shown that a combination of Bayesian Regularization and Validation Stopping is superior to just one.
What version of the NN Toolbox do you have?
You should be able to combine VALSTOPPING and MSEREG with TRAINLM. I'm not sure about doing it with TRAINSCG.
If you are successful with the combination, please post.
Hope this helps.
Thank you for formally accepting my answer
Greg

更多回答（1 个）

Lorenzo Ridolfi
Lorenzo Ridolfi 2017-7-23

0 个投票

Thank you for the answer. I'm using 2016b. Do you have any link to a publication about combination of Bayesian Regularization and Validation Stopping?
Best Regards, Lorenzo

类别

在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 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