Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- Gaussian process assumes the target data to be distributed as a multivariate Gaussian, with Gaussian noise.
- This is often an unreasonable assumption to make for the raw data
- Standard practice is to apply a preprocessing transformation in an ad-hoc manner preceding the modelling with the GP
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement