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

September 02, 2018 • 01:01:48

BI 007 Daniel Yamins: Infant AI and CNNs

Mentioned in the show: Dan’s Stanford Neuroscience and Artificial Intelligence Laboratory: The 2 papers we discuss Performance-optimized hierarchical models predict neural responses in higher...

Episode 0

June 16, 2021 • 01:26:12

BI 108 Grace Lindsay: Models of the Mind

Grace’s websiteTwitter: @neurograce.Models of the Mind: How Physics, Engineering and Mathematics Have Shaped Our Understanding of the Brain.We talked about Grace’s work using convolutional...

Episode 0

December 22, 2019 • 01:27:37

BI 056 Tom Griffiths: The Limits of Cognition

Support the show on Patreon for almost nothing. I speak with Tom Griffiths about his “resource-rational framework”, inspired by Herb Simon's bounded rationality and...