BI 051 Jess Hamrick: Mental Simulation and Construction

Brain Inspired

Oct 27 2019 | 01:28:21

00:00 / 01:28:21

Show Notes

Support the Podcast

Jess and I discuss construction using graph neural networks. She makes AI agents that build structures to solve tasks in a simulated blocks and glue world using graph neural networks and deep reinforcement learning. We also discuss her work modeling mental simulation in humans and how it could be implemented in machines, and plenty more.

Show notes:

Jess’s website.
Follow her on twitter: @jhamrick
The papers we discuss or mention:
- Analogues of mental simulation and imagination in deeplearning.
- Structured agents for physical construction.
- Relational inductive biases, deep learning, and graph networks.
  - Build your own graph networks: Open source graph network library.

Other Episodes

Episode

March 27, 2019 • 01:04:40

BI 030 Jay McClelland: Mathematical Reasoning and PDP

Jay's homepage at Stanford.Implementing mathematical reasoning in machines:The video lecture.The paper.Parallel Distributed Processing by Rumelhart and McClelland.Complimentary Learning Systems Theory and Its Recent Update.Episode...

Episode 0

August 26, 2021 • 01:13:56

BI 112 Ali Mohebi and Ben Engelhard: The Many Faces of Dopamine

BI 112: Ali Mohebi and Ben Engelhard The Many Faces of Dopamine Announcement: Ben has started his new lab and is recruiting grad students....

Episode 0

October 18, 2018 • 00:41:34

BI 014 Konrad Kording: Regulators, Mount Up!

Show Notes: Follow Konrad on Twitter: @KordingLab. Konrad's lab website. The paper we discuss: Bioscience-scale automated detection of figure element reuse.