how to achieve parameter sharing in the deep learning design?

in the deep learing design, is there a way to achieve an intermidiate layer, and this layer can accept varied length of inputs, each input is processed using the same learnable parameters.

Answer 1

[Mathy]

Hi Zini,

If the Deep Learning Toolbo doesn't offer the specific layer you need for your task, you have the option to create your own custom layer. You can learn more about defining a custom deep layer with formatted inputs by visiting this link:

https://www.mathworks.com/help/deeplearning/ug/define-custom-deep-learning-layer-with-formatted-inputs.html

Hope this helps!