cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Choose Language Hide Translation Bar

Gaussian Processes (moving it from Specialized to Predictive Modeling)

Gaussian Processes are a very powerful modeling technique in predictive analytics.

https://scikit-learn.org/stable/modules/gaussian_process.html

 

While JMP has GP, it is only for specialized modeling (not possible to fit using training/validation/test)

FN_0-1594376713832.png

FN_1-1594376861744.png

 

 

2 Comments
moeckelr
Level II

Addition of different Kernels (matern, etc) would be highly benefitial for general modellig as well.

eryximachos
Level I
  • Kernels would be great, e.g. choosable: periodic, linear trend, noisy, smoothness-parameter and free kernels.
  • Additionally it would be great if you could include the uncertainty of the input data points.
  • An easy function to find the (next n) point(s) of highest variance in a specified input-range would help to find the best next experimental point(s). Of course this can by done by a script, but a menue entry for this would make it much easier for non-scripters.