Key Interests: Representation Learning, Vision, Biological Inspiration & Inductive Bias, Equivariant Representations, Alignment
Hello! Iโm currently a PhD Candidate at Sorbonne Universityโs 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 ๐ง .
Previously, I worked as a Research Engineer in Brice Bathellierโs 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 Iโm 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 youโre interested in any of our MLJC projects or share similar interests.
News
SoS workshop @Cosyne2024 Confirmed Speakerโs List
CoSyNe 2024 is fast approaching ! Are you interested in vision neuroscience? ๐ง ๐๏ธ
— Simone Azeglio (@simoneazeglio) February 16, 2024
Then join us on March 2 in Cascais, Portugal ๐ต๐น https://t.co/J3ZbIfoKbO
SoS workshop @Cosyne2024 is taking place
Excited about #VisionNeuroscience ? Join us at #CoSyNe2024 in Cascais, Portugal on March 5th! Dive into "Sharpening Our Sight" - a workshop on efficient neural representations & active vision. ๐๐ง https://t.co/hlaEBv7mt2
— Simone Azeglio (@simoneazeglio) January 30, 2024
NeurReps @NeurIPS 2023 is taking place!
Join us this Saturday at #NeurIPS2023 ๐ง ๐คฏ https://t.co/STwJOlR11H
— Simone Azeglio (@simoneazeglio) December 11, 2023
NeurReps submission deadline gets extended!
NeurReps deadline got extended to Friday Oct 6 ๐ฅณ Some more time for your submissions! https://t.co/5YHQrqsTPh
— Simone Azeglio (@simoneazeglio) October 5, 2023
Group Theory in Neuroscience @ Symmetry, Invariance and Neural Representations
NeurReps deadline got extended to Friday Oct 6 ๐ฅณ Some more time for your submissions! https://t.co/5YHQrqsTPh
— Simone Azeglio (@simoneazeglio) October 5, 2023
Symmetry, Invariance and Neural Representations is happening again @ Bernstein 2023
๐ข Exciting News! Join us at the ๐๐๐๐จ๐ง๐ ๐๐จ๐ซ๐ค๐ฌ๐ก๐จ๐ฉ ๐จ๐ง ๐๐ฒ๐ฆ๐ฆ๐๐ญ๐ซ๐ฒ, ๐๐ง๐ฏ๐๐ซ๐ข๐๐ง๐๐, ๐๐ง๐ ๐๐๐ฎ๐ซ๐๐ฅ ๐๐๐ฉ๐ซ๐๐ฌ๐๐ง๐ญ๐๐ญ๐ข๐จ๐ง๐ฌ, co-organized by @ari_dibe and myself, at #BernsteinConference 2023. ๐ pic.twitter.com/qhiFMOf1mD
— Simone Azeglio (@simoneazeglio) August 4, 2023
Art and AIโs Video Representations @ Sorbonne
What can we learn if we try to reverse engineer 3D Convolutional Neural Networks? A sneak peek into a small part of Kaspar Ravel's exposition: "quelques formes discretes" at @Sorbonne_Univ_ ๐๏ธ๐ผ๏ธ
— Simone Azeglio (@simoneazeglio) May 30, 2023
A short ๐งต on this joint work https://t.co/ovKPfIjEln
NeurReps Proceedings are out ๐
It took a while, but finally the proceedings of our (with Sophia Sanborn, Christian Shewmake, Arianna Di Bernardo and Nina Miolane) workshop are out ๐
๐ The wait is over! ๐
— Simone Azeglio (@simoneazeglio) March 17, 2023
The proceedings for the 2022 NeurIPS Workshop on Symmetry and Geometry in Neural Representations have arrived! Dive into the cutting-edge research and insights on PMLR now! ๐ง ๐ฅ@NeurIPSConf @neur_reps https://t.co/Nrs0bKpboB
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, โIdV_ENSโ got 3rd and I had the chance to present our work at NeurIPS 2022 ๐ญ๐ง
#NeurIPS2022 is not over yet ! Today (3.30 pm CST) I'll give a short online talk on our - w/ Ulisse Ferrari, Peter Neri (@lsp_ens) and @RetinaGeek - approach for the Sensorium Competition on modeling mice V1, which allowed us to finish 3rd ๐ญ https://t.co/alNZLgZD4M
— Simone Azeglio (@simoneazeglio) December 6, 2022
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 youโre interested in following further developments at the intersection of Neuroscience, Deep Learning and Geometry donโt hesitate to join our community on Slack
If you're at #NeurIPS2022 you can't miss our workshop โจ https://t.co/HsDbqv19ln
— Simone Azeglio (@simoneazeglio) December 2, 2022
Our Workshop has been accepted @NeurIPS 2022
Our workshop on Symmetry and Geometry in Neural Representations has been accepted to @NeurIPSConf 2022! Weโve put together a lineup of incredible speakers and panelists from ๐ง neuroscience, ๐ค geometric deep learning, and ๐ geometric statistics.
Glad to be part of the organizing committee of this @NeurIPSConf workshop!
— Simone Azeglio (@simoneazeglio) July 8, 2022
Further updates as well as a call for papers are coming soon ๐
With @naturecomputes @cashewmake2 @ari_dibe @ninamiolane https://t.co/VmLEG4DIf7
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.
Deeply pleased and honored to receive this award ! Can't wait to present our work at the #BernsteinConference.
— Simone Azeglio (@simoneazeglio) June 13, 2022
Thanks @BathellierL, @institutpasteur for your support ๐ง https://t.co/7ofJXFNkDp
Symmetry, Invariance and Neural Representations
Azeglio & Di Bernardo, Symmetry, Invariance and Neural Representations Bernstein Conference 2022
It's official! @BernsteinNeuro accepted our - with @ari_dibe - workshop proposal ๐ง
— Simone Azeglio (@simoneazeglio) May 7, 2022
In "Symmetry, Invariance and Neural Representations" we will explore the intimate relationship between the physical world and neural representations.
Join our speakers in this experience! pic.twitter.com/eOisKkGGum
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
#cosyne2022 was awesome! I had the pleasure to present our work at the @brain_score workshop(https://t.co/VFa7r7YvZy), as part of the selected models submitted to the Brain-Score competition. TLDR: We employed a Gated Recurrent Convolutional Network w/ some fancy augmentation pic.twitter.com/Iv6sSdpSRo
— Simone Azeglio (@simoneazeglio) March 25, 2022