Suivre
Guillaume Lajoie
Guillaume Lajoie
Assistant Professor, Applied Mathematics, Université de Montréal
Adresse e-mail validée de umontreal.ca - Page d'accueil
Titre
Citée par
Citée par
Année
Gradient starvation: A learning proclivity in neural networks
M Pezeshki, O Kaba, Y Bengio, AC Courville, D Precup, G Lajoie
Advances in Neural Information Processing Systems 34, 1256-1272, 2021
2562021
Learning function from structure in neuromorphic networks
LE Suárez, BA Richards, G Lajoie, B Misic
Nature Machine Intelligence 3 (9), 771-786, 2021
862021
Dimensionality compression and expansion in deep neural networks
S Recanatesi, M Farrell, M Advani, T Moore, G Lajoie, E Shea-Brown
arXiv preprint arXiv:1906.00443, 2019
772019
Non-normal recurrent neural network (nnrnn): learning long time dependencies while improving expressivity with transient dynamics
G Kerg, K Goyette, M Puelma Touzel, G Gidel, E Vorontsov, Y Bengio, ...
Advances in neural information processing systems 32, 2019
752019
Learning to combine top-down and bottom-up signals in recurrent neural networks with attention over modules
S Mittal, A Lamb, A Goyal, V Voleti, M Shanahan, G Lajoie, M Mozer, ...
International Conference on Machine Learning, 6972-6986, 2020
712020
Predictive learning as a network mechanism for extracting low-dimensional latent space representations
S Recanatesi, M Farrell, G Lajoie, S Deneve, M Rigotti, E Shea-Brown
Nature communications 12 (1), 1417, 2021
602021
Implicit regularization via neural feature alignment
A Baratin, T George, C Laurent, RD Hjelm, G Lajoie, P Vincent, ...
International Conference on Artificial Intelligence and Statistics, 2269-2277, 2021
542021
Chaos and reliability in balanced spiking networks with temporal drive
G Lajoie, KK Lin, E Shea-Brown
Physical Review E—Statistical, Nonlinear, and Soft Matter Physics 87 (5 …, 2013
532013
Systematic evaluation of causal discovery in visual model based reinforcement learning
NR Ke, A Didolkar, S Mittal, A Goyal, G Lajoie, S Bauer, D Rezende, ...
arXiv preprint arXiv:2107.00848, 2021
392021
Is a modular architecture enough?
S Mittal, Y Bengio, G Lajoie
Advances in Neural Information Processing Systems 35, 28747-28760, 2022
352022
On lyapunov exponents for rnns: Understanding information propagation using dynamical systems tools
R Vogt, M Puelma Touzel, E Shlizerman, G Lajoie
Frontiers in Applied Mathematics and Statistics 8, 818799, 2022
352022
Gradient-based learning drives robust representations in recurrent neural networks by balancing compression and expansion
M Farrell, S Recanatesi, T Moore, G Lajoie, E Shea-Brown
Nature Machine Intelligence 4 (6), 564-573, 2022
282022
Untangling tradeoffs between recurrence and self-attention in artificial neural networks
G Kerg, B Kanuparthi, AG ALIAS PARTH GOYAL, K Goyette, Y Bengio, ...
Advances in Neural Information Processing Systems 33, 19443-19454, 2020
262020
Reliability of cka as a similarity measure in deep learning
MR Davari, S Horoi, A Natik, G Lajoie, G Wolf, E Belilovsky
arXiv preprint arXiv:2210.16156, 2022
252022
Driving reservoir models with oscillations: a solution to the extreme structural sensitivity of chaotic networks
P Vincent-Lamarre, G Lajoie, JP Thivierge
Journal of computational neuroscience 41, 305-322, 2016
252016
Multi-view manifold learning of human brain-state trajectories
EL Busch, J Huang, A Benz, T Wallenstein, G Lajoie, G Wolf, ...
Nature computational science 3 (3), 240-253, 2023
242023
A connectomics-based taxonomy of mammals
LE Suarez, Y Yovel, MP van den Heuvel, O Sporns, Y Assaf, G Lajoie, ...
Elife 11, e78635, 2022
242022
Recurrent neural networks learn robust representations by dynamically balancing compression and expansion
M Farrell, S Recanatesi, T Moore, G Lajoie, E Shea-Brown
BioRxiv, 564476, 2019
222019
Structured chaos shapes spike-response noise entropy in balanced neural networks
G Lajoie, JP Thivierge, E Shea-Brown
Frontiers in computational neuroscience 8, 123, 2014
222014
Multi-scale feature learning dynamics: Insights for double descent
M Pezeshki, A Mitra, Y Bengio, G Lajoie
International Conference on Machine Learning, 17669-17690, 2022
202022
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20