Artificial Intelligence and You
Technology
This and all episodes at: https://aiandyou.net/ .
Training an AI to render accurate decisions for important questions can be useless and dangerous if it cannot tell you why it made those decisions. Enter explainability, a term so new that it isn't in spellcheckers but is critical to the successful future of AI in critical applications.
Before I talked with Michael Hind, my usual remark on the subject was, "If you want a demonstration of the ultimate futility of explainability, try asking your kid how the vase got broken." But after this episode I've learned more than I thought possible about how we can teach AI what an explanation is and how to produce one.
Michael is a Distinguished Research Staff Member in the IBM
Research AI department in Yorktown Heights, New York. His current
research passion is the area of Trusted AI, focusing on governance,
transparency, explainability, and fairness of AI systems. He helped launch several successful open source projects, such as
AI Fairness 360 and AI Explainability 360.
All this plus our usual look at today's AI headlines.
Transcript and URLs referenced at HumanCusp Blog.
092 - Guest: Ben Shneiderman, Human-Centered AI Expert, part 2
091 - Guest: Ben Shneiderman, Human-Centered AI Expert, part 1
090 - Guest: David Danks, Professor of Philosophy and Data Science, part 2
089 - Guest: David Danks, Professor of Philosophy and Data Science, part 1
088 - Special Panel: AI in Music
087 - Guest: Stuart Russell, AI professor, author, activist, part 2
086 - Guest: Stuart Russell, AI professor, author, activist, part 1
085 - Guest: David Brin, Science Fiction Author and Scientist, part 2
084 - Guest: David Brin, Science Fiction Author and Scientist, part 1
083 - Guest: René Morkos, AI for Construction CEO
082 - Guest: Kush Varshney, AI Trustworthiness Research Scientist
081 - Guest: Tannya Jajal, AI Innovator and Author
080 - Special Panel: AI Predictions for 2022
079 - Guest: John Zerilli, Cognitive Science Philosopher, part 2
078 - Guest: John Zerilli, Cognitive Science Philosopher, part 1
077 - Guest: Alexandra Mousavizadeh, Strategic Intelligence Media Producer, part 2
076 - Guest: Alexandra Mousavizadeh, Strategic Intelligence Media Producer, part 1
075 - Guest: Michael Hind, IBM AI Explainability Expert, part 2
073 - Guest: Kordel France, AI Engineer and CEO, part 2
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
The Unbelivable Truth - Series 1 - 26 including specials and pilot
Lex Fridman Podcast