Azeem’s Picks: Demis Hassabis on DeepMind’s Journey from Games to Fundamental Science
Azeem Azhar's Exponential View
00:00
AI XI: A Deep Learning System
In a sense, you've got an intelligent agent. And if it takes a good action that helps it get to it objective, it gets some kind of positive reinforcement. If it takes the wrong kind of action, it gets a negative reinforcement and so on. That's exactly right. You know, in fact, one of the things that Shane Leg, my co-founder and chief scientist, did for his PhD was to analyze a system called AI XI, AIXC,. It's actually an amazing mathematical framework for what intelligence is - still not that well known as fascinating.
Transcript
Play full episode
