Stephane Deny
@stphtphsn.bsky.social
Assistant Professor at Aalto. Neuro - ML https://scholar.google.com/citations?hl=fr&user=Z3jU6mQAAAAJ&view_op=list_works&authuser=1&sortby=pubdate
Pinned
Stephane Deny
@stphtphsn.bsky.social
· Jan 14
New Preprint: "On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory" by Andrea Perin and myself. Retweets of this post or the thread below are highly appreciated! Follow @zazzarazzaz.bsky.social for future updates on this line of work.
🔥 Technical blog post (with maths and code) on how to render 4D objects, by Raihan Gafur 🔥
🔗 raihanthecooldude.com/spaceland-ep...
🔗 raihanthecooldude.com/spaceland-ep...
November 8, 2025 at 8:32 AM
🔥 Technical blog post (with maths and code) on how to render 4D objects, by Raihan Gafur 🔥
🔗 raihanthecooldude.com/spaceland-ep...
🔗 raihanthecooldude.com/spaceland-ep...
Reposted by Stephane Deny
Happy to share my first work with a connection to myopia, a collaboration with EssilorLuxottica
www.science.org/doi/10.1126/...
www.science.org/doi/10.1126/...
Nonlinear spatial integration allows the retina to detect the sign of defocus in natural scenes
The retina can easily detect whether the eye is too small or too big thanks to the imperfections of the eye optics.
www.science.org
October 25, 2025 at 9:07 PM
Happy to share my first work with a connection to myopia, a collaboration with EssilorLuxottica
www.science.org/doi/10.1126/...
www.science.org/doi/10.1126/...
Reposted by Stephane Deny
How does our brain excel at complex object recognition, yet get fooled by simple illusory contours? What unifying principle governs all Gestalt laws of perceptual organization?
We may have an answer: integration of learned priors through feedback. New paper with @kenmiller.bsky.social! 🧵
We may have an answer: integration of learned priors through feedback. New paper with @kenmiller.bsky.social! 🧵
October 24, 2025 at 2:00 PM
How does our brain excel at complex object recognition, yet get fooled by simple illusory contours? What unifying principle governs all Gestalt laws of perceptual organization?
We may have an answer: integration of learned priors through feedback. New paper with @kenmiller.bsky.social! 🧵
We may have an answer: integration of learned priors through feedback. New paper with @kenmiller.bsky.social! 🧵
🔥 "The Perception and Learning of 4D Object Geometry in Humans and Machines" 🔥
Master thesis work by Raihan Gafur.
Check out his awesome blog post series!
raihanthecooldude.com/spaceland-ep...
Master thesis work by Raihan Gafur.
Check out his awesome blog post series!
raihanthecooldude.com/spaceland-ep...
Spaceland – Ep. 01 – When the Brain Meets the Fourth Dimension: Exploring Mental Rotation in 4D Objects – Raihan Gafur
raihanthecooldude.com
October 16, 2025 at 3:01 PM
🔥 "The Perception and Learning of 4D Object Geometry in Humans and Machines" 🔥
Master thesis work by Raihan Gafur.
Check out his awesome blog post series!
raihanthecooldude.com/spaceland-ep...
Master thesis work by Raihan Gafur.
Check out his awesome blog post series!
raihanthecooldude.com/spaceland-ep...
Reposted by Stephane Deny
Palestinians have for years pointed out how Microsoft, HPE, AWS — virtually the entire tech industry — has enthusiastically assisted occupation and genocide of Palestinians. Only now, because the tide is turning, can a story like this get mainstream attention. Zionism is in trouble.
September 26, 2025 at 4:18 AM
Palestinians have for years pointed out how Microsoft, HPE, AWS — virtually the entire tech industry — has enthusiastically assisted occupation and genocide of Palestinians. Only now, because the tide is turning, can a story like this get mainstream attention. Zionism is in trouble.
Reposted by Stephane Deny
(1/6) Thrilled to share our triple-N dataset (Non-human Primate Neural Responses to Natural Scenes)! It captures thousands of high-level visual neuron responses in macaques to natural scenes using #Neuropixels.
May 11, 2025 at 1:33 PM
(1/6) Thrilled to share our triple-N dataset (Non-human Primate Neural Responses to Natural Scenes)! It captures thousands of high-level visual neuron responses in macaques to natural scenes using #Neuropixels.
Reposted by Stephane Deny
(1/6) Excited to share a new preprint from our lab! Can large, deep nonlinear neural networks trained with indirect, low-dimensional error signals compete with full-fledged backpropagation? Tl;dr: Yes! arxiv.org/abs/2502.20580.
Training Large Neural Networks With Low-Dimensional Error Feedback
Training deep neural networks typically relies on backpropagating high dimensional error signals a computationally intensive process with little evidence supporting its implementation in the brain. Ho...
arxiv.org
March 23, 2025 at 9:23 AM
(1/6) Excited to share a new preprint from our lab! Can large, deep nonlinear neural networks trained with indirect, low-dimensional error signals compete with full-fledged backpropagation? Tl;dr: Yes! arxiv.org/abs/2502.20580.
Reposted by Stephane Deny
This is great stuff!
I think about this a lot. Thanks @behrenstimb.bsky.social for the wonderfully 90s-vibe blog full of wisdom!
users.fmrib.ox.ac.uk/~behrens/Sta...
users.fmrib.ox.ac.uk/~behrens/Sta...
March 18, 2025 at 9:25 AM
This is great stuff!
Reposted by Stephane Deny
A comparison between humans and AI at recognizing objects in unusual poses
Netta Ollikka, Amro Kamal Mohamed Abbas, Andrea Perin, Markku Kilpeläinen, Stephane Deny
Action editor: Andrew Lampinen
https://openreview.net/forum?id=yzbAFf8vd5
#poses #recognition #recognizing
Netta Ollikka, Amro Kamal Mohamed Abbas, Andrea Perin, Markku Kilpeläinen, Stephane Deny
Action editor: Andrew Lampinen
https://openreview.net/forum?id=yzbAFf8vd5
#poses #recognition #recognizing
February 13, 2025 at 5:07 AM
A comparison between humans and AI at recognizing objects in unusual poses
Netta Ollikka, Amro Kamal Mohamed Abbas, Andrea Perin, Markku Kilpeläinen, Stephane Deny
Action editor: Andrew Lampinen
https://openreview.net/forum?id=yzbAFf8vd5
#poses #recognition #recognizing
Netta Ollikka, Amro Kamal Mohamed Abbas, Andrea Perin, Markku Kilpeläinen, Stephane Deny
Action editor: Andrew Lampinen
https://openreview.net/forum?id=yzbAFf8vd5
#poses #recognition #recognizing
hmm, thanks gpt, that's very clear now what a MRAC is
February 9, 2025 at 1:25 PM
hmm, thanks gpt, that's very clear now what a MRAC is
Reposted by Stephane Deny
New Preprint: "On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory" by Andrea Perin and myself. Retweets of this post or the thread below are highly appreciated! Follow @zazzarazzaz.bsky.social for future updates on this line of work.
January 14, 2025 at 2:25 PM
New Preprint: "On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory" by Andrea Perin and myself. Retweets of this post or the thread below are highly appreciated! Follow @zazzarazzaz.bsky.social for future updates on this line of work.
Reposted by Stephane Deny
Interesting work on symmetries and learning!
Little is known about how deep networks interact with structure in data. An important aspect of this structure is symmetry (e.g., pose transformations). Here, we (w/ @stphtphsn.bsky.social) study the generalization ability of deep networks on symmetric datasets: arxiv.org/abs/2412.11521 (1/n)
On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory
Symmetries (transformations by group actions) are present in many datasets, and leveraging them holds significant promise for improving predictions in machine learning. In this work, we aim to underst...
arxiv.org
January 14, 2025 at 5:23 PM
Interesting work on symmetries and learning!
Reposted by Stephane Deny
Now published in @elife.bsky.social doi.org/10.7554/eLif... a fun collaboration with
@clairemb90.bsky.social and Rainer Friedrich
@clairemb90.bsky.social and Rainer Friedrich
Geometry and dynamics of representations in a precisely balanced memory network related to olfactory cortex
Computational modeling revealed that balanced assemblies of excitatory and inhibitory neurons shape representational manifolds in olfactory cortex-like recurrent networks, resulting in joint maps of s...
doi.org
January 14, 2025 at 10:04 AM
Now published in @elife.bsky.social doi.org/10.7554/eLif... a fun collaboration with
@clairemb90.bsky.social and Rainer Friedrich
@clairemb90.bsky.social and Rainer Friedrich
Reposted by Stephane Deny
I did my PhD with Ed Deci, who usually says very few words. In our meetings, it was his reserved nature that gradually allowed me to come out of my shell, be my own person. That experience teaches me one valuable lesson now that I mentor others: know when to shut up.
January 14, 2025 at 2:50 PM
I did my PhD with Ed Deci, who usually says very few words. In our meetings, it was his reserved nature that gradually allowed me to come out of my shell, be my own person. That experience teaches me one valuable lesson now that I mentor others: know when to shut up.
New Preprint: "On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory" by Andrea Perin and myself. Retweets of this post or the thread below are highly appreciated! Follow @zazzarazzaz.bsky.social for future updates on this line of work.
January 14, 2025 at 2:25 PM
New Preprint: "On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory" by Andrea Perin and myself. Retweets of this post or the thread below are highly appreciated! Follow @zazzarazzaz.bsky.social for future updates on this line of work.
Reposted by Stephane Deny
Little is known about how deep networks interact with structure in data. An important aspect of this structure is symmetry (e.g., pose transformations). Here, we (w/ @stphtphsn.bsky.social) study the generalization ability of deep networks on symmetric datasets: arxiv.org/abs/2412.11521 (1/n)
On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory
Symmetries (transformations by group actions) are present in many datasets, and leveraging them holds significant promise for improving predictions in machine learning. In this work, we aim to underst...
arxiv.org
January 14, 2025 at 1:05 PM
Little is known about how deep networks interact with structure in data. An important aspect of this structure is symmetry (e.g., pose transformations). Here, we (w/ @stphtphsn.bsky.social) study the generalization ability of deep networks on symmetric datasets: arxiv.org/abs/2412.11521 (1/n)
Reposted by Stephane Deny
Pre-print 🧠🧪
Is mechanism modeling dead in the AI era?
ML models trained to predict neural activity fail to generalize to unseen opto perturbations. But mechanism modeling can solve that.
We say "perturbation testing" is the right way to evaluate mechanisms in data-constrained models
1/8
Is mechanism modeling dead in the AI era?
ML models trained to predict neural activity fail to generalize to unseen opto perturbations. But mechanism modeling can solve that.
We say "perturbation testing" is the right way to evaluate mechanisms in data-constrained models
1/8
January 8, 2025 at 4:33 PM
Pre-print 🧠🧪
Is mechanism modeling dead in the AI era?
ML models trained to predict neural activity fail to generalize to unseen opto perturbations. But mechanism modeling can solve that.
We say "perturbation testing" is the right way to evaluate mechanisms in data-constrained models
1/8
Is mechanism modeling dead in the AI era?
ML models trained to predict neural activity fail to generalize to unseen opto perturbations. But mechanism modeling can solve that.
We say "perturbation testing" is the right way to evaluate mechanisms in data-constrained models
1/8
Reposted by Stephane Deny
Cutting it a bit fine, but here’s my review of the year in neuroscience for 2024
The eighth of these, would you believe? We’ve got dark neurons, tiny monkeys, the most complete brain wiring diagram ever constructed, and much more…
Published on The Spike
Enjoy!
medium.com/the-spike/20...
The eighth of these, would you believe? We’ve got dark neurons, tiny monkeys, the most complete brain wiring diagram ever constructed, and much more…
Published on The Spike
Enjoy!
medium.com/the-spike/20...
2024: A Review of the Year in Neuroscience
Feeling a bit wired
medium.com
December 30, 2024 at 4:00 PM
Cutting it a bit fine, but here’s my review of the year in neuroscience for 2024
The eighth of these, would you believe? We’ve got dark neurons, tiny monkeys, the most complete brain wiring diagram ever constructed, and much more…
Published on The Spike
Enjoy!
medium.com/the-spike/20...
The eighth of these, would you believe? We’ve got dark neurons, tiny monkeys, the most complete brain wiring diagram ever constructed, and much more…
Published on The Spike
Enjoy!
medium.com/the-spike/20...
Reposted by Stephane Deny
thinking of calling this "The Illusion Illusion"
(more examples below)
(more examples below)
December 1, 2024 at 2:33 PM
thinking of calling this "The Illusion Illusion"
(more examples below)
(more examples below)
Reposted by Stephane Deny
The Center for Neural Science at NYU is aiming to add another computational neuroscientist to our community: apply.interfolio.com/157767
Come join us!
Deadline 31 Dec 2024
Come join us!
Deadline 31 Dec 2024
Apply - Interfolio
{{$ctrl.$state.data.pageTitle}} - Apply - Interfolio
apply.interfolio.com
November 26, 2024 at 3:22 AM
The Center for Neural Science at NYU is aiming to add another computational neuroscientist to our community: apply.interfolio.com/157767
Come join us!
Deadline 31 Dec 2024
Come join us!
Deadline 31 Dec 2024