Setting more than one final output in the fitrnet function

10 次查看（过去 30 天）
FERNANDO CALVO RODRIGUEZ
回答： Samyuktha 2023-4-5
Hi!
I am trying to make a neural network with cross validation with the fitnet function and I can't find anything to do it with. So I looked in the bibliography and the fitnet function allows to do it with the big disadvantage that it only allows one response output. My model has a few more so it gives me error and I do not know how to modify this structure or if it is possible.
If someone knows something it would be of great help!
Translated with www.DeepL.com/Translator (free version)

请先登录，再回答此问题。

回答（1 个）

Samyuktha
Samyuktha 2023-4-5
Hi Fernando,
I understand that you are trying to modify the 'fitrnet' function.
In R2021a, SMLT introduced the fitting function 'fitrnet', which trains the shallow classification and regression neural network models. You can adjust the number of outputs for the fully connected layers by specifying the 'LayerSizes' name-value argument.
Please refer to the following documentation link for more information:
fitrnet
Hope it helps!!

类别

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

标签

产品


版本

R2022b

Community Treasure Hunt

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

Start Hunting!

Translated by