BI 021 Matt Botvinick: Neuroscience and AI at DeepMind

Brain Inspired

Dec 11 2018 | 01:19:39

00:00 / 01:19:39

Show Notes

Show notes:

DeepMind.
The papers we discuss:
- Neuroscience-Inspired Artificial Intelligence.
- A nice summary of the meta-reinforcement learning work.
- Learning to reinforcement learn.
- Prefrontal cortex as a meta-reinforcement learning system.
- Machine Theory of Mind.
Reinforcement learning.

Other Episodes

Episode 0

August 02, 2018 • 01:11:23

BI 002 Steven Potter Part 2: Brains in Dishes

Find out more about Steve at his website. Things mentioned during the show: Papers we talked about: Publishing negative results! Wagenaar, D. A., Pine,...

Episode 0

September 20, 2018 • 01:04:46

BI 010 Adam Marblestone: Brain Cost Functions

Mentioned in the show Adam’s Website. Follow him on Twitter. He made Technology Review’s 35 Innovators Under 35. The paper we discuss: Toward an...

Episode 0

May 15, 2020 • 01:47:07

BI 070 Bradley Love: How We Learn Concepts

Brad and I discuss his battle-tested, age-defying cognitive model for how we learn and store concepts by forming and rearranging clusters, how the model...