Sign in

Roy Eyono

@royeyono.bsky.social
532 followers 562 following 13 posts

PhD Student in NeuroAI @Mila and @McGill

PostsRepliesMedia
Reposted by Roy Eyono
Aaron Milstein @neurosutras.bsky.social · 20/03/2026
This is an important one. That soma-targeting interneurons can do background subtraction and gain modulation is well understood. But the roles of dendrite-targeting interneurons in normalizing top-down learning signals have not been studied in detail.
22612
Roy Eyono @royeyono.bsky.social · 19/03/2026
Wouldn't have been possible without you! Thanks Dan!!
011
Reposted by Roy Eyono
Blake Richards @tyrellturing.bsky.social · 19/03/2026
Here's a lovely #blueprint on a new study from our lab led by @royeyono.bsky.social. tl;dr: it implies that there may be interneurons whose role is to normalize credit assignment signals during learning. #neuroscience 🧪
25012
Roy Eyono @royeyono.bsky.social · 19/03/2026
🫶 This work was done in collaboration with @dlevenstein.bsky.social @tyrellturing.bsky.social @arnaghosh.bsky.social @repromancer.bsky.social Check out the full paper to dive deeper into our findings! Paper: arxiv.org/abs/2603.17676
arxiv.org
Inhibitory normalization of error signals improves learning in neural circuits
Normalization is a critical operation in neural circuits. In the brain, there is evidence that normalization is implemented via inhibitory interneurons and allows neural populations to adjust to chang...
070
Roy Eyono @royeyono.bsky.social · 19/03/2026
These findings complement several theories on how SST-subtypes targeting apical dendrites (where error-related signals arrive) are critical in supporting learning. Potentially, via the normalization of error signals! e.g. Payeur et al. : nature.com/articles/s41...
150
Roy Eyono @royeyono.bsky.social · 19/03/2026
Hence this led us to believe if the brain uses inhibition for normalization, it must have a dedicated mechanism to normalize learning signals! tldr; In the end, we found that centering the gradients via lateral inhibition was enough to recapitulate performance on the task!
180
Roy Eyono @royeyono.bsky.social · 19/03/2026
Upon further inspection, we indeed noticed that despite our high alignment in neural activity, we had poor gradient alignment with layer norm.
140
Roy Eyono @royeyono.bsky.social · 19/03/2026
Why you may ask? It turns out that layer normalization actually implicitly normalizes back-propagated error signals "under the hood" !
130
Roy Eyono @royeyono.bsky.social · 19/03/2026
Surprisingly! Despite successfully normalizing feedforward neural activity, this didn't reflect in performance. As we were unable to recapitulate layer normalization's performance on the task.
120
Roy Eyono @royeyono.bsky.social · 19/03/2026
With our simple inhibitory loss function on our EI network, we were able to successfully *learn* to layer normalize neural activity!
151
Roy Eyono @royeyono.bsky.social · 19/03/2026
Our network was trained on a robust perceptual invariance task: FashionMNIST with randomized brightness levels during both training and testing. (bounded by epsilon)
141
Roy Eyono @royeyono.bsky.social · 19/03/2026
The brain is believed to recruit inhibitory neurons to perform normalization, but how does it actually help us learn?🤔 To find out, we built an ANN with separate excitatory and inhibitory neurons. And trained the E weights on the task and the I weights to do layer normalization
140
Roy Eyono @royeyono.bsky.social · 19/03/2026
How do neural circuits in the brain implement normalization? 🧠 In our new paper, we show that just normalizing sensory input isn't enough. Crucially, we must also normalize the error signals! 🧵👇 Paper: arxiv.org/abs/2603.17676
arxiv.org
Inhibitory normalization of error signals improves learning in neural circuits
Normalization is a critical operation in neural circuits. In the brain, there is evidence that normalization is implemented via inhibitory interneurons and allows neural populations to adjust to chang...
16922
Reposted by Roy Eyono
Dan Levenstein @dlevenstein.bsky.social · 23/06/2025
Thrilled to announce I'll be starting my own neuro-theory lab, as an Assistant Professor at @yaleneuro.bsky.social @wutsaiyale.bsky.social this Fall! My group will study offline learning in the sleeping brain: how neural activity self-organizes during sleep and the computations it performs. 🧵
6142549
Reposted by Roy Eyono
Timothy O'Leary @timothyoleary.bsky.social · 17/12/2024
Apropos of never ending discussions about whether ANNs are "good" models of the nervous system, here is a slide I present to masters students showing a network that is found in motor control circuits *across phyla* (that's pretty ubiquitous!) I ask them to guess what it does...
616663
Reposted by Roy Eyono
Blake Richards @tyrellturing.bsky.social · 16/12/2024
1/ Okay, one thing that has been revealed to me from the replies to this is that many people don't know (or refuse to recognize) the following fact: The unts in ANN are actually not a terrible approximation of how real neurons work! A tiny 🧵. 🧠📈 #NeuroAI #MLSky
2115238
Reposted by Roy Eyono
Tim Behrens @behrenstimb.bsky.social · 01/12/2024
OK If we are moving to Bluesky I am rescuing my favourite ever twitter thread (Jan 2019). The renamed: Bluesky-sized history of neuroscience (biased by my interests)
14635205
Reposted by Roy Eyono
Jonathan Cornford @repromancer.bsky.social · 29/11/2024
Delighted to be in Leeds joining the School of Computing! Fantastic first impressions — like a "less offensive London" (youtu.be/watch?v=_6_VVLgrgFI). Stay tuned for a PhD position starting next October. Meanwhile, drop me a message with your CV and research interests—I'd love to hear from you!
0349
Roy Eyono @royeyono.bsky.social · 24/11/2024
9️⃣
000
Reposted by Roy Eyono
Colin Bredenberg @colin-bredenberg.bsky.social · 08/10/2024
1. Hi all: I’m here to advertise our new preprint: www.biorxiv.org/content/10.1..., with Fabrice Normandin, @tyrellturing.bsky.social, and @glajoie.bsky.social!
biorxiv.org
The oneirogen hypothesis: modeling the hallucinatory effects of classical psychedelics in terms of replay-dependent plasticity mechanisms
Classical psychedelics induce complex visual hallucinations in humans, generating percepts that are coherent at a low level, but which have surreal, dream-like qualities at a high level. While there a...
35612
Roy Eyono @royeyono.bsky.social · 26/09/2024
I have admired Thomas Sankara for as long as I can remember. In this blog, I put myself in his shoes and imagine what he would have thought of this new age of AI. Thought this would be fitting as my inaugural post on BlueSky!
royeyono.substack.com
Afro-Centric Effective Altruism: A Sankaran Essay
Afro-futurism: What would Thomas Sankara think about AI, and its implications on the African diaspora.
050