You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When using the Polynomial kernel in GPflow and setting degree=2, the model still seems to fit a linear relationship rather than the expected quadratic relationship. The figure below shows the same model with the same kernel function which is kernel=gpflow.kernels.Polynomial(offset=p_offset, variance=p_variance, degree=2). However, when predicting two similar X, the results are different, which seems to be the difference in degree. So I'm wondering is it possible that when fitting the data, the degree is treated as a parameter that can be adjusted? If the answer is no, what are the possible reasons for this result?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
When using the Polynomial kernel in GPflow and setting degree=2, the model still seems to fit a linear relationship rather than the expected quadratic relationship. The figure below shows the same model with the same kernel function which is kernel=gpflow.kernels.Polynomial(offset=p_offset, variance=p_variance, degree=2). However, when predicting two similar X, the results are different, which seems to be the difference in degree. So I'm wondering is it possible that when fitting the data, the degree is treated as a parameter that can be adjusted? If the answer is no, what are the possible reasons for this result?
Beta Was this translation helpful? Give feedback.
All reactions