Hyperparameter tuning of neural network

3 次查看（过去 30 天）

Itachi 2019-7-20

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/472641-hyperparameter-tuning-of-neural-network

评论： Qiang Wang 2021-2-3

Hi guys,

I need a code to find the optimum configuration of a neural network. I mean the number of hidden layers and their corresponding neurons. I found the following topic but there's nothing on the number of hidden layers.

Please, can anyone help me? Thanks in advance.

https://nl.mathworks.com/matlabcentral/answers/428298-neural-network-hyperparameter-tuning

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。

回答（1 个）

Greg Heath 2019-7-21

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/472641-hyperparameter-tuning-of-neural-network#answer_384115

One hidden layer is always sufficient. However, sometimes

1. Knowledge of the physical or mathematical process may lead to a better understanding using multiple hidden layers

2. Multiple hidden layers can be used to minimze the total number of hidden layer weights that have to be estimated.

Hope this helps.

Thank you for formally accepting my answer

Greg

3 个评论
显示 1更早的评论隐藏 1更早的评论

Gunbir Singh Baveja 2020-5-3

i have the same question

Qiang Wang 2021-2-3

referee ask me same question about why I only tuning nurons number in one hiddne layer.

How to response? Thank you.

请先登录，再进行评论。

请先登录，再回答此问题。

类别

AI, Data Science, and Statistics Deep Learning Toolbox Sequence and Numeric Feature Data Workflows

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

产品

版本

R2019a

Community Treasure Hunt

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

Start Hunting!

Translated by