Choose Language Hide Translation Bar

Neural Network third layer

I know there is a lot that can be done with two layers, but being limited with two layers even in JMP Pro is not a good idea. As a customer, I can get any layer in a free package of Python and I don't know why I should not be able to get the same with JMP Pro. Number of layers in the best option would be selective, otherwise, at least provide three layers (Input, middle, output layers).

Tracking Number:

Defect ID: S1573906

2 Comments
Level I

I'm actually advocating for a minimum of 5 layers, though 3 layers would be a good start!  I want to do nonlinear data compression,  in a like form of autoencoders-decoders.  The middle layer would have the lowest count, and I think in general 5 layers for this kind of data compression makes sense.

Level II

Probably they can include a drop down menu to select how many layers are required and leave it to the user.