What is Wrong with Explainable AI? | AISC
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=E_EaJxkuh4k
For slides and more information on the paper, visit https://ai.science/e/what-is-wrong-with-explainable-ai--NLg93Ur152G3sWVJnpKl
Speaker: Peter Condon; Host: Ali El-Sharif
Motivation:
Peter will present his view of the limitations of existing XAI techniques (LIME, Shapley Values, Partial Dependence Plot, Saliency Maps, Counterfactual Explanations & Rule Extraction) and introduce his novel proposed framework - RAY (Restructure, Assess, Yank)
------
#AISC hosts 3-5 live sessions like this on various AI research, engineering, and product topics every week! Visit https://ai.science for more details