| 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 | 76 | 2019 |
| Catastrophic fisher explosion: Early phase fisher matrix impacts generalization S Jastrzebski, D Arpit, O Astrand, GB Kerg, H Wang, C Xiong, R Socher, ... International Conference on Machine Learning, 4772-4784, 2021 | 67 | 2021 |
| h-detach: Modifying the LSTM gradient towards better optimization B Kanuparthi, D Arpit, G Kerg, NR Ke, I Mitliagkas, Y Bengio International Conference on Learning Representations, 2018 | 50* | 2018 |
| 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 | 27 | 2020 |
| Safe screening for support vector machines J Zimmert, CS de Witt, G Kerg, M Kloft NIPS 2015 Workshop on Optimization in Machine Learning (OPT), 2015 | 24 | 2015 |
| On neural architecture inductive biases for relational tasks G Kerg, S Mittal, D Rolnick, Y Bengio, B Richards, G Lajoie arXiv preprint arXiv:2206.05056, 2022 | 22 | 2022 |
| Continuous-time meta-learning with forward mode differentiation T Deleu, D Kanaa, L Feng, G Kerg, Y Bengio, G Lajoie, PL Bacon arXiv preprint arXiv:2203.01443, 2022 | 22 | 2022 |
| Goal-driven optimization of single-neuron properties in artificial networks reveals regularization role of neural diversity and adaptation V Geadah, S Horoi, G Kerg, G Wolf, G Lajoie bioRxiv, 2022.04. 29.489963, 2022 | 5 | 2022 |
| Inductive biases for relational tasks G Kerg, S Mittal, D Rolnick, Y Bengio, BA Richards, G Lajoie ICLR2022 Workshop on the Elements of Reasoning: Objects, Structure and Causality, 2022 | 5 | 2022 |
| Advantages of biologically-inspired adaptive neural activation in RNNs during learning V Geadah, G Kerg, S Horoi, G Wolf, G Lajoie arXiv preprint arXiv:2006.12253, 2020 | 4 | 2020 |
| Neural networks with optimized single-neuron adaptation uncover biologically plausible regularization V Geadah, S Horoi, G Kerg, G Wolf, G Lajoie bioRxiv, 2023 | 1 | 2023 |
| Inductive biases for efficient information transfer in artificial networks G Kerg | | 2023 |
| Learning Long-term Dependencies Using Cognitive Inductive Biases in Self-attention RNNs G Kerg, B Kanuparthi, A Goyal, K Goyette, Y Bengio, G Lajoie | | |
Guillaume LajoieAssistant Professor, Applied Mathematics, Université de MontréalVerified email at umontreal.ca
