Stéphane Deny

Neuroscience & AI

Aalto University, Espoo, Finland


I am assistant professor at Aalto University (Finland), in the departments of Neuroscience and Computer Science.
I am currently setting up a lab at the interface of neuroscience and artificial intelligence.

Featured Publications

Humans Beat Deep Networks at Recognizing Objects in Unusual Poses, Given Enough Time

Netta Ollikka, Amro Abbas, Andrea Perin, Markku Kilpeläinen, Stéphane Deny

arXiv 2024 

A comparison between the human visual system, and state-of-the-art computer vision systems, at recognizing objects in unusual poses. 

ViewFusion: Learning Composable Diffusion Models for Novel View Synthesis

Bernard Spiegl, Andrea Perin, Stéphane Deny, Alexander Ilin

arXiv 2024 

A state-of-the-art generative approach to novel view synthesis with unparalleled flexibility.

On the special role of class-selective neurons in early training

Omkar Ranadive, Nikhil Thakurdesai, Ari S Morcos, Matthew Leavitt, Stéphane Deny

TMLR 2024 

Deep networks exhibit class-selective neurons in all their layers. Intriguingly, it was recently shown that these neurons aren’t crucial for network function. So, why do they even exist? Our study reveals the special role they play in early training... (more on Twitter)

Blockwise Self-Supervised Learning at Scale

Shoaib Ahmed Siddiqui, David Krueger, Yann LeCun, Stéphane Deny

ArXiv 2023 / Code 

An attempt at scaling a local learning rule based on self-supervised learning to ImageNet, with promising results... (more on Twitter)

Progress and limitations of deep networks to recognize objects in unusual poses

Amro Abbas, Stéphane Deny

AAAI 2023 / Code 

A thorough evaluation of the capability of state-of-the-art deep networks to recognize objects in unusual poses. 

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

Jure Zbontar*, Li Jing*, Ishan Misra, Yann LeCun, Stéphane Deny

ICML 2021 / Code 

A simple method for state-of-the-art self-supervised learning, inspired by a 60-year-old principle from neuroscience... (more on Twitter)

Addressing the Topological Defects of Disentanglement via Distributed Operators

Diane Bouchacourt*, Mark Ibrahim*, Stéphane Deny

arXiv 2021 / Code 

We use topological arguments to show that disentanglement as commonly defined introduces discontinuities in the encoder, which leads us to propose a new approach to disentanglement through distributed equivariant operators... (more on Twitter)

A Unified Theory of Early Visual Representations from Retina to Cortex  through Anatomically Constrained Deep CNNs

Jack Lindsey*, Samuel A. Ocko*, Surya Ganguli, Stéphane Deny

International Conference on Learning Representations (ICLR 2019) / Code 

Visual representations differ drastically between the retina and primary visual cortex, and retinal representations also differ across species. We reproduce these biological properties by varying neural resource constraints in a deep convolutional model of the visual system... (more on Twitter)

The emergence of multiple retinal cell types through efficient coding of natural movies

Samuel A. Ocko*, Jack Lindsey*, Surya Ganguli, Stéphane Deny

Advances in Neural Information Processing Systems (NeurIPS 2018) / Code / PDF

Why are there so many parallel pathways at the output of the retina? Convolutional autoencoders, that optimally encode natural movies with low firing rates, use exactly the same channels that primates use in their retina... (more on Twitter)

Multiplexed computations in retinal ganglion cells of a single type

Stéphane Deny, Ulisse Ferrari, Emilie Macé, Pierre Yger, Romain Caplette, Serge Picaud, Gašper Tkačik & Olivier Marre 

Nature Communications 2017 / PDF

By fitting convolutional neural neworks to retinal responses, we find that certain cell types multiplex linear and non-linear computations with the help of a sophisticated gain control mechanism. 

Optogenetic vision restoration with high resolution

Ulisse Ferrari*, Stéphane Deny*, Abhishek Sengupta*, Romain Caplette, José-Alain Sahel, Deniz Dalkara, Serge Picaud, Jens Duebel, Olivier Marre

BiorXiv 2018 / PDF

Using Bayesian methods, we estimate an upper bound on the acuity that blind people could recover from optogenetic therapy.

Learning stable representations in a changing world with on-line t-SNE: proof of concept in the songbird

Stéphane Deny*, Emily Mackevicius*, Tatsuo Okubo, Gordon Berman, Joshua Shaevitz, Michale Fee

International Conference on Learning Representations Workshop Track (ICLR 2016) / PDF

By adapting t-SNE to streaming time series, we track the evolution of syllables in the developing songbird.

More Publications

Coupling of activity, metabolism and behaviour across the Drosophila brain

Mann K.*,  Deny S.*,  Ganguli S., Clandinin T. R., Nature 2021 

Separating intrinsic interactions from extrinsic correlations in a network of sensory neurons

Ferrari U., Deny S., Chalk M., Tkačik G., Marre O., Mora T.  Physical Review E 2018 / PDF

A simple model for low variability in neural spike trains

Ferrari U., Deny S., Marre O., Mora T.  Neural Computation 2018 / PDF

Nonlinear decoding of a complex movie from the mammalian retina

Botella-Soler V., Deny S., Marre O., Tkacik G.  PLoS Computational Biology 2018 / PDF

A spike sorting toolbox for up to thousands of electrodes validated with ground truth recordings in vitro and in vivo

Yger P., Spampinato G.L.B, Esposito E., Lefebvre B., Deny S., Gardella C., Stimberg M., Jetter F., Zeck G., Picaud S., Duebel J., Marre O.  eLife 2018 / PDF

Dynamical criticality in the collective activity of a population of retinal neurons

Mora T., Deny S., Marre O.  Physical Review Letters 2015 / PDF

*equal contribution.


Local and Non-local Processing in the Retina (PhD thesis)

Deny S.  Paris-Sorbonne University VI (2017) / PDF

Surprise Decoding in the Retinal Activity (MS neuroscience thesis)

Deny S.  Pierre and Marie Curie University (2013) / PDF 

Implementation of a bio-inspired recurrent convolutional neural network for image recognition and threat detection (MS computer science thesis, in french)

Deny S. Ecole Superieure d'Electricite (Supelec) (2012) / PDF