apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-09 12:02:38 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Corrected mistake in gradients: Was finding d(Xi-Xj)/dOffset instead of dr/dOffset. Fixed by scaling by kernel lengthscale.

Browse source
This commit is contained in:
Michael T Smith 2016-08-04 09:01:27 +01:00
parent 04bcf56de1
commit ebe4a496a6
1 changed files with 4 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
GPy/models/gp_offset_regression.py
View file

@ -75,6 +75,10 @@ class GPOffsetRegression(GP):
#print Gs[i]
#print w
dr_doffsets.append(dr_doffset)
#lastly we need to divide by the lengthscale: So far we've found d(X_i - X_j)/dOffsets
#we want dr/dOffsets. (X_i - X_j)/lengthscale = r
dr_doffsets /= self.kern.lengthscale
return dr_doffsets
def parameters_changed(self):