Number of Neurons in a model

2011 12 16
1 个回答
5 次查看（30 天）

1 个投票

Hi everyone,
I have another confusion
Is there any thumb rule or relation between number of neurons in hidden layer and input variables? suppose, I have a data set with 10 input variables. By hit and trial method, how many neurons maximum can I try? I understand that as number of neurons increase, correlation and mse also improves. But at same time, network gets overtrained. How can I be sure that I am not overtraining the network?
Thanks
Arijit

请先登录，再回答此问题。

回答（1 个）

Ahmad Taher
Ahmad Taher 2012-1-19

1 个投票

Dear Colleague
Hope the following link may help you: http://www.faqs.org/faqs/ai-faq/neural-nets/part3/section-10.html
If you have 10 input variables, I suggest to start with 10 neurons and try different numbers to 20 neurons and then select the best numbers with least MSE.

类别

在 帮助中心 和 File Exchange 中查找有关 Neural Simulation 的更多信息

标签

提问:

Arijit
Arijit
2011-12-16

Community Treasure Hunt

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

Start Hunting!

Translated by