Skip to content

gecko/out-of-distribution-model-behaviour

Repository files navigation

out-of-distribution-model-behaviour


Just visualizing for a couple of non-linear models how the predictions develop, when confronted with sample data out of the trained distribution. The modeling methods are:

  • Support Vector Regression
  • Random Forrest
  • Gradient Booster
  • Simple Feed Forward Network
  • Regression Tree
  • Gaussean Process

The data is some arbitrary trigonometric surface in 3d space.

About

Just visualizing for a couple of models what they predict ot of their learned distribution

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published