Explainable Learning with Gaussian Processes

arXiv:2403.07072v1 Announce Type: new
Abstract: The field of explainable artificial intelligence (XAI) attempts to develop methods that provide insight into how complicated machine learning methods make predictions. Many methods of explanation have focused on the concept of feature attribution, a decomposition of the model's prediction into individual contributions corresponding to each input feature. In this work, we explore the problem of feature attribution in the context of Gaussian process regression (GPR). We take a principled approach to defining attributions under …

arxiv cs.lg eess.sp gaussian processes processes type