Borrar filtros
Borrar filtros

Setting more than one final output in the fitrnet function

18 visualizaciones (últimos 30 días)
FERNANDO CALVO RODRIGUEZ
FERNANDO CALVO RODRIGUEZ el 31 de Mzo. de 2023
Respondida: Samyuktha el 5 de Abr. de 2023
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)

Respuestas (1)

Samyuktha
Samyuktha el 5 de Abr. de 2023
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:
Hope it helps!!

Productos


Versión

R2022b

Community Treasure Hunt

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

Start Hunting!

Translated by