Giancarlo Kerg

According to our database, Giancarlo Kerg authored at least 8 papers between 2019 and 2022.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2022

On Neural Architecture Inductive Biases for Relational Tasks.

Giancarlo Kerg, Sarthak Mittal, David Rolnick, Yoshua Bengio, Blake A. Richards, Guillaume Lajoie

CoRR, 2022

Continuous-Time Meta-Learning with Forward Mode Differentiation.

Tristan Deleu, David Kanaa, Leo Feng, Giancarlo Kerg, Yoshua Bengio, Guillaume Lajoie, Pierre-Luc Bacon

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization.

Stanislaw Jastrzebski, Devansh Arpit, Oliver Åstrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof J. Geras

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Advantages of biologically-inspired adaptive neural activation in RNNs during learning.

Victor Geadah, Giancarlo Kerg, Stefan Horoi, Guy Wolf, Guillaume Lajoie

CoRR, 2020

Untangling tradeoffs between recurrence and self-attention in neural networks.

Giancarlo Kerg, Bhargav Kanuparthi, Anirudh Goyal, Kyle Goyette, Yoshua Bengio, Guillaume Lajoie

CoRR, 2020

Untangling tradeoffs between recurrence and self-attention in artificial neural networks.

Giancarlo Kerg, Bhargav Kanuparthi, Anirudh Goyal, Kyle Goyette, Yoshua Bengio, Guillaume Lajoie

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics.

Giancarlo Kerg, Kyle Goyette, Maximilian Puelma Touzel, Gauthier Gidel, Eugene Vorontsov, Yoshua Bengio, Guillaume Lajoie

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

h-detach: Modifying the LSTM Gradient Towards Better Optimization.

Bhargav Kanuparthi, Devansh Arpit, Giancarlo Kerg, Nan Rosemary Ke, Ioannis Mitliagkas, Yoshua Bengio

Proceedings of the 7th International Conference on Learning Representations, 2019