Giancarlo Kerg | DeepAI

DeepAI AI Chat

Featured Co-authors

Yoshua Bengio
448 publications
Kyunghyun Cho
218 publications
Caiming Xiong
210 publications
Richard Socher
111 publications
Huan Wang
82 publications
Anirudh Goyal
61 publications
Guy Wolf
50 publications
Ioannis Mitliagkas
46 publications
Gauthier Gidel
46 publications
Nan Rosemary Ke
33 publications
David Rolnick
31 publications

∙ 06/09/2022

On Neural Architecture Inductive Biases for Relational Tasks

Current deep learning approaches have shown good in-distribution general...

20 Giancarlo Kerg, et al. ∙

∙ 03/02/2022

Continuous-Time Meta-Learning with Forward Mode Differentiation

Drawing inspiration from gradient-based meta-learning methods with infin...

0 Tristan Deleu, et al. ∙

∙ 12/28/2020

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization

The early phase of training has been shown to be important in two ways f...

16 Stanisław Jastrzębski, et al. ∙

∙ 06/22/2020

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

Dynamic adaptation in single-neuron response plays a fundamental role in...

18 Victor Geadah, et al. ∙

∙ 06/16/2020

Untangling tradeoffs between recurrence and self-attention in neural networks

Attention and self-attention mechanisms, inspired by cognitive processes...

0 Giancarlo Kerg, et al. ∙

∙ 05/28/2019

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

A recent strategy to circumvent the exploding and vanishing gradient pro...

1 Giancarlo Kerg, et al. ∙

∙ 10/06/2018

h-detach: Modifying the LSTM Gradient Towards Better Optimization

Recurrent neural networks are known for their notorious exploding and va...

0 Devansh Arpit, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world