Guillaume Lajoie (@g_lajoie_) 's Twitter Profile
Guillaume Lajoie

@g_lajoie_

Associate Prof. @UMontreal Math & Stats and @MILAMontreal, @ai_unique Applied Math, AI, Computational Neuroscience, Neural Interfacing

ID: 1072220386237009921

linkhttps://www.guillaumelajoie.com calendar_today10-12-2018 20:03:55

593 Tweet

1,1K Followers

224 Following

UNIQUE Center Neuro-AI (@ai_unique) 's Twitter Profile Photo

Breaking News: Registration + Abstract submission for Montreal #AI & #Neuroscience (MAIN 2024) are now open ! 🎉🎉 Join us for an in-person meeting in Montreal October 22-25th ! Register now (limited space): 👉 main2024.org Abstract submission deadline: 15 Oct!

Breaking News: Registration + Abstract submission for Montreal #AI & #Neuroscience (MAIN 2024) are now open ! 🎉🎉

Join us for an in-person meeting in Montreal October 22-25th ! 

Register now (limited space):

👉  main2024.org

Abstract submission deadline: 15 Oct!
Guillaume Lajoie (@g_lajoie_) 's Twitter Profile Photo

New preprint where we ask if the psychedelic-induced hallucinations can be explained by the role of dendrites in learning mechanisms in the brain. In short: classical psychedellics might hijack physiological gating mechanisms in generative learning. biorxiv.org/content/10.110…

Mila - Institut québécois d'IA (@mila_quebec) 's Twitter Profile Photo

Mila's annual supervision request process opens on October 15 to receive MSc and PhD applications for Fall 2025 admission! Join our community! More information here mila.quebec/en/prospective…

Mila's annual supervision request process opens on October 15 to receive MSc and PhD applications for Fall 2025 admission! Join our community! More information here mila.quebec/en/prospective…
Karim Jerbi (@karimjerbineuro) 's Twitter Profile Photo

Last 24h to register for MAIN 2024 happening in Montreal next week! 👉 main2024.org Also check-out the Educational day on Oct 25th (which requires separate registration). 🧠 🤖 🥯 🐼 #Neuroscience #AI #Montreal

Last 24h to register for MAIN 2024 happening in Montreal next week!

👉 main2024.org

Also check-out the Educational day on Oct 25th (which requires separate registration).

🧠 🤖 🥯 🐼 

#Neuroscience #AI #Montreal
Eric Elmoznino (@ericelmoznino) 's Twitter Profile Photo

1/5 Very excited to announce our new paper that formally defines compositionality, giving us theoretical insight into what it actually is and helping us build it into AI models. This was work with Thomas Jiralerspong, Yoshua Bengio, and Guillaume Lajoie. arxiv.org/abs/2410.14817…

Guillaume Lajoie (@g_lajoie_) 's Twitter Profile Photo

In-context learnin (ICL) is one of the most exciting part of the LLM boom. Sequence models (not just LLMs) implement on-the-fly models conditionned on inputs w/o weight updates! Q: are in-context models better than «in-weights» ones? A: some times ICL is better than standard opt.

Guillaume Lajoie (@g_lajoie_) 's Twitter Profile Photo

Compositional representations are a key attributes of intelligent systems that generalize well. An issue is that there is no robust way to quantify compositionality. Below is our attempt at such a quantifiable measurement. w/ Eric Elmoznino Thomas Jiralerspong Yoshua Bengio

Jack Lindsey (@jack_w_lindsey) 's Twitter Profile Photo

Really excited to share our work on crosscoders, a generalization of sparse autoencoders that allows us to identify shared structure across layers or even across models, greatly simplifying our description of model representations. transformer-circuits.pub/2024/crosscode…

Really excited to share our work on crosscoders, a generalization of sparse autoencoders that allows us to identify shared structure across layers or even across models, greatly simplifying our description of model representations.  transformer-circuits.pub/2024/crosscode…
Jonathan (@jhcornford) 's Twitter Profile Photo

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

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
Jonathan (@jhcornford) 's Twitter Profile Photo

Roman Pogodin Arna Ghosh Blake Richards Mila - Institut québécois d'IA I’m thrilled to announce I’ll be joining University of Leeds School of Computing to work on resource efficient AI and theories of biological intelligence! If you’re interested in work like this, I’ll be recruiting PhD students and postdocs. Please reach out or forward this on! 12/12

<a href="/rmnpogodin/">Roman Pogodin</a> <a href="/arna_ghosh/">Arna Ghosh</a> <a href="/tyrell_turing/">Blake Richards</a> <a href="/Mila_Quebec/">Mila - Institut québécois d'IA</a> I’m thrilled to announce I’ll be joining <a href="/UniversityLeeds/">University of Leeds</a> School of Computing to work on resource efficient AI and theories of biological intelligence! If you’re interested in work like this, I’ll be recruiting PhD students and postdocs. Please reach out or forward this on! 12/12
Guillaume Lajoie (@g_lajoie_) 's Twitter Profile Photo

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/journa… Props to Victor Geadah and co-authors

Brokoslaw Laschowski (@drlaschowski) 's Twitter Profile Photo

Talk by Guillaume Lajoie at the Montreal AI and Neuroscience (MAIN) Conference on credit assignment in neural networks without plasticity. #neuroscience #neuroAI #AI #compneuro youtube.com/watch?v=CvCqz5…

CosyneMeeting (@cosynemeeting) 's Twitter Profile Photo

Recruiting phd/postdocs to mentor Undergrad Awardees!! This program brings UGs from across the 🌎 considering a career in neuro research Duties: meet students on 1st day, take them to a poster session, help them feel welcome. Apply: (very short!) form forms.gle/9hCniCA29ky59x…

Guillaume Lajoie (@g_lajoie_) 's Twitter Profile Photo

As sequence models and in-context conditioning for inference are being developed to perform all kinds of ML tasks, we make systematic and tracktable evaluations to compare point v.s. distributional estimates . imo a key step to scale predictive modeling for general ML

Mila - Institut québécois d'IA (@mila_quebec) 's Twitter Profile Photo

La stimulation du nerf vague (VNS) représente une innovation prometteuse dans le traitement de maladies chroniques comme l'épilepsie ou la dépression, entre autres. Découvrez comment des chercheurs de Mila utilisent l’apprentissage automatique pour identifier en temps réel les

La stimulation du nerf vague (VNS) représente une innovation prometteuse dans le traitement de maladies chroniques comme l'épilepsie ou la dépression, entre autres. Découvrez comment des chercheurs de Mila utilisent l’apprentissage automatique pour identifier en temps réel les
Guillaume Lajoie (@g_lajoie_) 's Twitter Profile Photo

Recent progress on foundation-like models for neural data. As many use cases for generalizable models demand flexible online deployment, here we focus on a design enabling low latency real time use. We use hybrid SSM architecture & demonstrate various transfer learning scenarios