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 0

November 27, 2019 • 01:15:24

BI 054 Kanaka Rajan: How Do We Switch Behaviors?

Kanaka and I discuss a few different ways she uses recurrent neural networks to understand how brains give rise to behaviors. We talk about...

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.

Episode

August 25, 2018 • 00:37:16

BI 006 Ryan Poplin: Deep Solutions

[bctt tweet="Check out episode 6 of the Brain Inspired podcast: Deep learning, eyeballs, and brains" username="pgmid"] Mentioned in the show Ryan Poplin What is...