46 min listen
BI 051 Jess Hamrick: Mental Simulation and Construction
FromBrain Inspired
ratings:
Length:
88 minutes
Released:
Oct 27, 2019
Format:
Podcast episode
Description
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.
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.
Released:
Oct 27, 2019
Format:
Podcast episode
Titles in the series (100)
BI 005 David Sussillo: RNNs are Back!: Mentioned in the show: David’s Twitter account Papers we discuss: Sussillo, D.S. & Abbott, L. F. (2009). Generating Coherent Patterns of Activity from Chaotic Neural Networks. Neuron 63(4). Sussillo, D. (2014) Neural circuits as computational by Brain Inspired