We are investigating Deep Learning for predictive modeling to identify instrument subsystem failures using R and Python packages. Since Deep Learning is similar to neural nets, perhaps these can be used as the basis of a script to expand the number of layers. Deep Learning would be a good tool for future versions of JMP Pro.
It sounds like a great idea.
To insure that the JMP folks officially receive your suggestion, you need to send it directly to them, at
Or post this into the JMP Wish List at the menu bar. Then others can Cudo it to make it more important.