Suppose I trained a Gaussian process classifier with a linear kernel (using GPML toolbox) and got some feature weights for each input feature.

My question is then:

Does it/When does it make sense to interpret the weights to indicate the real-life importance of each feature or interpret at group level the average over the weights of a group of features?

  • $\begingroup$ I'm voting to close this question because it was cross-posted. $\endgroup$ – D.W. Dec 5 '19 at 21:35