Explainable ArtificiaI Intelligence (XAI)

11/11/2017

AI is being used to find patterns in data, make decisions and take actions that impact billions of people around the world. There is increasing concern about the bias and inexplicability of AI, and urgent calls for transparency and accountability.

AI Explainers

  1. Logic on Coursera, Michael Genesereth, Stanford University
  2. A Primer on Reinforcement Learning, Nicholas Dawson, UTS

AI Inexplicability and AI Bias in the News:

  1. Computer says no: why making AIs fair, accountable and transparent is crucial, Nov 2017

  2. DARPA Explainable AI Program launched May 2017

Relevant papers:

Doshi-Velez, Finale, Mason Kortz, Ryan Budish, Chris Bavitz, Sam Gershman, David O'Brien, Stuart Schieber, James Waldo, David Weinberger, and Alexandra Wood. 2017. "Accountability of AI Under the Law: The Role of Explanation." arXiv [cs.AI], November. https://arxiv.org/abs/1711.01134.