Self-Explaining AI and some issues with present-day explainable AI techniques

Talk on my paper:
Self-explaining AI as an alternative to interpretable AI
arxiv.org/abs/2002.05149.

[@BijayRajPaudel]

Thank you for the paper and this video!

[@DistortedV12]

This was a very intelligent talk and paper. Thank you for sharing. I wonder if causality could also play a role here or if it is unecessary.