Simone Azeglio

Simone Azeglio

PhD Candidate at the Vision Institute & ร‰cole Normale Supรฉrieure

Key Interests: Representation Learning, Vision, Biological Inspiration & Inductive Bias, Equivariant Representations, Alignment

Hello! Iโ€™m currently a PhD Candidate at Sorbonne Universityโ€™s Vision Institute and Ecole Normale Superieure in Paris, under the supervision of Ulisse Ferrari, Olivier Marre and Peter Neri. My research interests revolve around uncovering the principles and symmetries that enable invariant and stable representations, with a focus on understanding biological learning, particularly in the context of vision. Specifically, in my main project, I am investigating the role of higher-order spatiotemporal correlations and how those can underlie invariance/equivariance and selectivity properties of the visual system ๐Ÿง .

Previously, I worked as a Research Engineer in Brice Bathellierโ€™s Lab at the Hearing Institute (Institut Pasteur), focusing on nonlinear network models for the auditory system. I also spent a few months working at CERN (with Lorenzo Moneta) and on nonlinear models of spatial memory at the University of Ottawa, under the supervision of Andrรฉ Longtin and Leonard Maler; my master thesis is available here.

Finally, I am the co-founder and member (ex-president) of a non-profit research organization, the Machine Learning Journal Club (MLJC), which focuses on interdisciplinary applications of Machine and Deep Learning. Through the MLJC, I have worked on scientific machine learning, brain-computer interfaces, and natural language processing, and Iโ€™m currently organizing a group on applications of geometric deep learning and the role of symmetries in the learning process. Please feel free to contact me if youโ€™re interested in any of our MLJC projects or share similar interests.

News

SoS workshop @Cosyne2024 Confirmed Speakerโ€™s List

SoS workshop @Cosyne2024 is taking place

NeurReps @NeurIPS 2023 is taking place!

NeurReps submission deadline gets extended!

Group Theory in Neuroscience @ Symmetry, Invariance and Neural Representations

Symmetry, Invariance and Neural Representations is happening again @ Bernstein 2023

Art and AIโ€™s Video Representations @ Sorbonne

NeurReps Proceedings are out ๐ŸŽ‰

It took a while, but finally the proceedings of our (with Sophia Sanborn, Christian Shewmake, Arianna Di Bernardo and Nina Miolane) workshop are out ๐ŸŽ‰

3rd Place in Sensorium Competition @NeurIPS 2022

Together with my supervisors: Ulisse Ferrari, Peter Neri and Olivier Marre, I took part in the Sensorium 2022 competition on predicting mice V1 (Primary Visual Cortex) neural activity with deep learning methods. Our team, โ€œIdV_ENSโ€ got 3rd and I had the chance to present our work at NeurIPS 2022 ๐Ÿญ๐Ÿง 

NeurReps: Symmetry and Geometry in Neural Representations is LIVE @NeurIPS 2022

Glad that our (together with Sophia Sanborn, Christian Shewmake, Arianna Di Bernardo and Nina Miolan) workshop, Symmetry and Geometry in Neural Representations a.k.a. NeurReps has been a truly enjoyable occasion. If youโ€™re interested in following further developments at the intersection of Neuroscience, Deep Learning and Geometry donโ€™t hesitate to join our community on Slack

Our Workshop has been accepted @NeurIPS 2022

Our workshop on Symmetry and Geometry in Neural Representations has been accepted to @NeurIPSConf 2022! Weโ€™ve put together a lineup of incredible speakers and panelists from ๐Ÿง  neuroscience, ๐Ÿค– geometric deep learning, and ๐ŸŒ geometric statistics.

Brains for Brains Award 2022

Since 2010, the Bernstein Network Computational Neuroscience presents the Brains for Brains Award, which recognizes the special achievements of young scientists who have shown their outstanding potential at a very early career stage โ€“ even before starting their doctoral studies. It is one of two prizes awarded bi-yearly by the Bernstein Network. This award aims to attract young international researchers to Germany.

Symmetry, Invariance and Neural Representations

Azeglio & Di Bernardo, Symmetry, Invariance and Neural Representations Bernstein Conference 2022

Improving Neural Predictivity in the Visual Cortex with Gated Recurrent Connections

Azeglio, Poetto, Savant-Aira, Nurisso, Improving Neural Predictivity in the Visual Cortex with Gated Recurrent Connections Brainscore Workshop - Cosyne 2022