cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Show  only  | Search instead for 
Did you mean: 
JMP Wish List

We want to hear your ideas for improving JMP software.

  1. Search: Please search for an existing idea first before submitting a new idea.
  2. Submit: Post your new idea using the Suggest an Idea button. Please submit one actionable idea per post rather than a single post with multiple ideas.
  3. Kudo & Comment Kudo ideas you like, and comment to add to an idea.
  4. Subscribe: Follow the status of ideas you like. Refer to status definitions to understand where an idea is in its lifecycle. (You are automatically subscribed to ideas you've submitted or commented on.)

We consider several factors when looking for what ideas to add to JMP. This includes what will have the greatest benefit to our customers based on scope, needs and current resources. Product ideas help us decide what features to work on next. Additionally, we often look to ideas for inspiration on how to add value to developments already in our pipeline or enhancements to new or existing features.

Choose Language Hide Translation Bar

Neural Network third layer

Status: Acknowledged Submitted by on ‎04-14-2020 04:18 PM
5 Comments (5 New)

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).

5 Comments
craigwb
Level I
‎10-13-2020 03:48 PM
‎10-13-2020 03:48 PM

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.

hnasiri
Level II
‎10-13-2020 04:02 PM
‎10-13-2020 04:02 PM

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

Sarah-Sylvestre
Staff
Staff
‎12-08-2022 02:31 PM
‎12-08-2022 02:31 PM
Status changed to: Acknowledged

Hi @hnasiri, thank you for your suggestion! We have captured your request and will take it under consideration.

FN
Level VI
‎02-18-2023 08:39 AM
‎02-18-2023 08:39 AM

What's the status of this? I agree we should have 5 rather than 3.

JMP 17 broke the possibility to use the same input as output, so we are out of luck even using one layer. In principle, they will revert it.


MikeD_Anderson
Staff
Staff
‎06-27-2024 11:10 AM
‎06-27-2024 11:10 AM

JMP 18 brings the Torch Add-in that provides access to these larger NN's: https://community.jmp.com/t5/JMP-Add-Ins/Torch-Deep-Learning-Add-In-for-JMP-Pro/ta-p/762296