Postdoc at @Mila_Quebec @UMontreal, studying motor learning and control.
Joined October 2017
- Tweets 2,408
- Following 297
- Followers 434
- Likes 2,644
60 Photos and videos
Olivier Codol retweeted
9 Jan 2025
Long time coming. A very cool project that showcases the advantages of single neuron adaptation in RNNs.
#PLOSCompBio: Neural networks with optimized single-neuron adaptation uncover biologically plausible regulari ... dx.plos.org/10.1371/journal.…
Props to @vgeadah and co-authors
8
30
1,271
Olivier Codol retweeted
27 Dec 2024
Excited to share my latest work with @DiedrichsenJorn and @andpru. In this work, we ask whether motor sequence learning is motoric at all! Check out the 🧵version of the abstract: biorxiv.org/content/10.1101/… 1/n
4
21
55
6,079
Olivier Codol retweeted
27 Dec 2024
Fantastic work by @mehrdadkashefi -- a deep investigation into the nature of learning motor sequences.
27 Dec 2024
Excited to share my latest work with @DiedrichsenJorn and @andpru. In this work, we ask whether motor sequence learning is motoric at all! Check out the 🧵version of the abstract: biorxiv.org/content/10.1101/… 1/n
6
21
2,036
Olivier Codol retweeted
23 Dec 2024
📢📢📢 Big paper out from the lab today! We show how motor circuits across cortex and thalamus do sensory planning and how this improves reaching.
2
14
85
8,032
Olivier Codol retweeted
8 Dec 2024
I’ll be attending #NeurIPS2024 in Vancouver this week. Excited to meet new people and chat about comp neuro, NeuroAI, and foundation models for neuroscience. Also keen to attend the NeuroAI, @unireps and @neur_reps workshops!
5
29
1,821
Olivier Codol retweeted
4 Nov 2024
It’s been a long time coming, but I’m thrilled to share my first research paper with @arna_ghosh , @ckaplanis1, @tyrell_turing, and Doina! Just accepted to NeurIPS 2024 (see u in Vancouver! 🇨🇦). This will be a longer thread—thanks for following along! arxiv.org/abs/2410.22133
1/11
3
25
152
15,696
1 Nov 2024
Check out Jonny's latest work on a bio-plausible synaptic learning rule that yield interesting properties in artificial neural networks! It was very exciting and fun to contribute to this work.
31 Oct 2024
Why does #compneuro need new learning methods? ANN models are usually trained with Gradient Descent (GD), which violates biological realities like Dale’s law and log-normal weights. Here we describe a superior learning algorithm for comp neuro: Exponentiated Gradients (EG)! 1/12
5
500
Olivier Codol retweeted
13 Sep 2024
For real, everyone in neuroscience and AI:
Get off this site. Elon is now using this platform to mess with American democracy. No one should be here anymore.
NeuroAI Bluesky is getting livelier every day. Please come join us.
2
6
29
3,789
26 Oct 2024
Interesting thread on convergence (or lack thereof) of neural solutions, with cool refs in the replies.
It seems a lot of studies focus on classification rather than control tasks, and oft simple input dynamics. I'm looking forward to seeing this further explored in the future.
21 Oct 2024
Is there a name for the hypothesis that task-trained neural networks and biological brains develop similar representations when they perform well, despite differences in architecture and learning methods? I.e. that optimization (whether backprop or evolution) leads to a similar solution?
If not, I think we should call it The Tolstoy Hypothesis: "All well-functioning networks are alike; each poorly functioning network is poor in its own way."
🤓💅
1
4
571
26 Oct 2024
The other unknown is whether this happens with different learning schemes, which could inject bias in the gradient. It wouldn't be surprising that this is more potent in forcing diff solutions as it directly alters the loss landscape, and the path taken on it during optimization
85
26 Oct 2024
Thank you to the @wusmsl for providing a great platform to exchange ideas and discuss science in-depth! Always a pleasure to interact with the folks down there, I warmly recommend
25 Oct 2024
No video this time around but @wusmsl was lucky to have lab alum @OlivierCodol present his recent work: "Brain-like neural dynamics for behavioral control develop through reinforcement learning". Check it out, definitely some food for thought! doi.org/10.1101/2024.10.04.6…
4
446
23 Oct 2024
There is no silver bullet
22 Oct 2024
To me, these results emphasize that scores are tools that need to be used along with domain expertise. In that view, model analyses - score-based or not- uncover to-be-tested hypotheses about how a model may capture an important brain-like mechanism. This is not a 1-d assessment.
2
173
Olivier Codol retweeted
22 Oct 2024
To me, these results emphasize that scores are tools that need to be used along with domain expertise. In that view, model analyses - score-based or not- uncover to-be-tested hypotheses about how a model may capture an important brain-like mechanism. This is not a 1-d assessment.
1
3
444
Olivier Codol retweeted
12 Oct 2024
I’ll be recruiting 1-2 graduate students for Fall 2025 to work on visual learning generalization in humans and artificial neural networks.
If you’re interested, apply!
Check out our lab website (snailab.ca) and reach out if you need more info.
RT please.
8 Oct 2024
📷 Meet our student community! Interested in joining Mila? Our annual supervision request process for admission in the fall of 2025 is starting on October 15, 2024. More information here mila.quebec/en/prospective-s…
5
85
248
42,496
Olivier Codol retweeted
8 Oct 2024
Investigating the experimentally-verifiable impact of different credit assignment mechanisms for learning in the brain is a crucial endeavor for computational neuroscience. Here: our take for motor learnning and the RL/SL question when looking at neural representations in cortex.
7 Oct 2024
Check out our new paper led by @OlivierCodol ! We use RNNs to explore possible learning rules that lead to the dynamics we see in brains during behavior.
biorxiv.org/content/10.1101/…
4
28
1,923
Olivier Codol retweeted
7 Oct 2024
Cool project on a topic that needs more investigation: the effect of the learning algo. on network activity & performance. Looking forward to more projects in that space -so many related questions to ask (effect of algorithm type, explor./noise, see also nature.com/articles/s41467-0…)!
7 Oct 2024
Here’s our latest work at @g_lajoie_ and @mattperich's labs! Excited to see this out.
We used a combination of neural recordings & modelling to show that RL yields neural dynamics closer to biology, with useful continual learning properties.
biorxiv.org/content/10.1101/…
1
5
730
Olivier Codol retweeted
7 Oct 2024
Check out our new paper led by @OlivierCodol ! We use RNNs to explore possible learning rules that lead to the dynamics we see in brains during behavior.
biorxiv.org/content/10.1101/…
7 Oct 2024
Here’s our latest work at @g_lajoie_ and @mattperich's labs! Excited to see this out.
We used a combination of neural recordings & modelling to show that RL yields neural dynamics closer to biology, with useful continual learning properties.
biorxiv.org/content/10.1101/…
8
33
5,664
7 Oct 2024
Here’s our latest work at @g_lajoie_ and @mattperich's labs! Excited to see this out.
We used a combination of neural recordings & modelling to show that RL yields neural dynamics closer to biology, with useful continual learning properties.
biorxiv.org/content/10.1101/…
2
13
43
7,347
7 Oct 2024
Finally, we show that the neural representations produced by RL have stabilization properties when fine-tuning to new environmental dynamics. Unlike supervised learning, this leads to representational reorganization that mirrors cortical plasticity in monkeys.
1
1
199
7 Oct 2024
We close up by discussing some of our views on learning and plasticity in cortical structures in the brain. Happy to chat more with anyone thinking about these questions!
2
175