2nd workshop on symmetry, invariance and neural representations

Organizers

Simone Azeglio | Vision Institute, Sorbonne University / Ecole Normale Supérieure, Paris, France

Arianna Di Bernardo | Ecole Normale Supérieure, Paris, France

Abstract

The second workshop on symmetry, invariance, and nneural representations at the Bernstein Conference 2023 seeks to encourage interdisciplinary research at the intersection of mathematics and neuroscience. The workshop will emphasize the significance of symmetries in the structure and function of the brain and present the latest research on neural population geometry, neural manifolds, embeddings of neural data, and invariant/equivariant neural representations in both biological and artificial networks. By incorporating geometric and topological features, along with symmetry, into the design of neural architectures, researchers can develop more interpretable and trainable models, leading to a more profound comprehension of the brain and its complexities. This ongoing research area has the potential to transform our understanding of neural computation and information processing, opening doors to more robust and efficient neural models. Building on the feedback and interaction with peers from the previous year, the second edition of this workshop will bring together researchers and students from various fields to promote cooperation and push forward this exciting research area.

Schedule (CEST)

Tuesday, Sept 26

14:00

Introduction and initial remarks
Simone Azeglio, Arianna Di Bernardo

14:10

Olivier Faugeras | National Institute for Research in Digital Science and Technology, France 
Past, present and future: invariance in neuroscience

14:40

Doris Tsao | University of California, USA 
A topological solution to object segmentation and tracking

15:25

Giovanna Citti (tbc) | University of Bologna, Italy 
Neurogeometrical models: functional architecture for motion and vision

16:00

30 min coffee break

16:30

Pierre-Etienne Fiquet | New York University, USA
Neural representation for predictive processing of dynamic visual signals

17:00

Christian Shewmake | University of California, USA
Tutorial on group invariant architectures: bispectral neural networks

17:30

Round table discussion
All workshop speakers

End of first day

Wednesday, Sept 27

08:30

Introduction to day 2
Simone Azeglio, Arianna Di Bernardo

08:40

Adam Gosztolai | Swiss Federal Institute of Technology in Lausanne, Switzerland
Interpretable statistical representations of neural population dynamics and geometry 

09:20

Federico Claudi (tbc) | Massachusetts Institute of Technology, USA
Manifold representation in continuous attractor neural networks: A general constructive approach

10:00

30 min coffee break

10:30

Benjamin Dunn | Norwegian University of Science and Technology, Norway
Developmental timeline of the grid cell torus

11:00

Alex Cayco-Gajic | Ecole Normale Supérieure, France
The learning dynamics of neural manifolds

11:30

Kristopher Jensen | University of Cambridge, UK
Tutorial: Studying the geometry and topology of neural population recordings with probabilistic generative models

12:00

Round table discussion
All workshop speakers

12:30

End