Schedule

8:15 - 8:30

Poster Organization 

Hanging posters (please hang your poster)

8:30 - 8:40

Opening remarks 

Noga Zaslavsky

8:40 - 9:10

The Physics of Science (Invited talk)

Karl Friston

9:10 - 9:20

States as goal-directed concepts: an epistemic approach to state-representation learning (Contributed talk

Nadav Amir, Yael Niv, Angela Langdon

9:20- 9:50

Human Information Processing in Complex Networks (Invited talk)

Dani S. Bassett

9:50 - 10:00

Discrete, compositional, and symbolic representations through attractor dynamics (Contributed talk

Andrew Nam, Eric Elmoznino, Nikolay Malkin, Chen Sun, Yoshua Bengio, Guillaume Lajoie

10:00 - 10:30

Coffee break + posters

10:30 - 11:00

Resource-rational prediction in real and artificial neural networks (Invited talk) 

Sarah Marzen

11:00 - 11:10

Lossy Compression and the Granularity of Causal Representation (Contributed talk)

David Kinney, Tania Lombrozo

11:10-11:40

Information Theory for Representation Learning (Invited talk) 

Alexander A. Alemi

11:40 - 12:00

Poster spotlights

What can AI Learn from Human Exploration? Intrinsically-Motivated Humans and Agents in Open-World ExplorationAlison Gopnik · Pieter Abbeel · Maria Rufova · Alyssa L Dayan · Eliza Kosoy · Yuqing Du
Active Vision with Predictive Coding and Uncertainty MinimizationAbdelrahman Sharafeldin · Nabil Imam · Hannah Choi
Natural Language Systematicity from a Constraint on Excess EntropyRichard Futrell
The Perception-Uncertainty Tradeoff in Generative Restoration ModelsRegev Cohen · Ehud Rivlin · Daniel Freedman
An Information-Theoretic Understanding of Maximum Manifold Capacity Representations, Rylan Schaeffer · Berivan Isik · Victor Lecomte · Mikail Khona · Yann LeCun · Andrey Gromov · Ravid Shwartz-Ziv · Sanmi Koyejo
Cognitive Information Filters: Algorithmic Choice Architecture for Boundedly Rational Choosers, Stefan Bucher · Peter Dayan 

12:00 - 13:30

Lunch break

13:30 - 14:00

An information perspective on language, cumulative culture, and human uniqueness (Invited talk)

Noah Goodman

14:00 - 14:10

Information theoretic study of the neural geometry induced by category learning (Contributed talk

Laurent BONNASSE-GAHOT, Jean-Pierre Nadal

14:10 - 14:40

Clustering and phase transitions in self-attention dynamics (Invited talk

Yury Polyanskiy

14:40 - 15:50

Poster session + coffee break

15:50 - 16:00

Information-Theoretic Generalization Error Bound of Deep Neural Networks (Contributed talk)

Haiyun He, Christina Yu, Ziv Goldfeld

16:00 - 16:55

Panel discussion: Information theory, cognition, and deep learning: Challenges and opportunities

Panelists: Sarah Marzen, Dani S. Bassett, Noah Goodman, Stephan Mandt

16:55 - 17:00

Closing remarks

17:00 - 17:30

Poster Organization

Removing posters (please remove your poster)