Professor Hima Lakkaraju presents some of the latest advancements in post hoc explanations for black-box machine learning models such as neural networks. Post hoc explanation techniques include local explanations such as feature importance, saliency maps, and counterfactuals as well as global explanations such as collections of local explanations, model distillation and summaries of counterfactuals.

View the full playlist: https://www.youtube.com/playlist?list=PLoROMvodv4rPh6wa6PGcHH6vMG9sEIPxL

#machinelearning