activity
20112026
most citedOn the difficulty of training Recurrent Neural Networks

3.8k citations · 6.5k across the 56 of their papers we have counts for

collaborators
Showing 2019Show all

12 papers · 1 filter

cs.LG201986 cited

Continual Unsupervised Representation Learning

Dushyant Rao, Francesco Visin, Andrei A. Rusu +3

Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially…

cs.LG2019132 cited

Stabilizing Transformers for Reinforcement Learning

Emilio Parisotto, H. Francis Song, Jack W. Rae +10

Owing to their ability to both effectively integrate information over long time horizons and scale to massive amounts of data, self-attention architectures have recently shown brea…

cs.NE2019

Improving the Gating Mechanism of Recurrent Neural Networks

Albert Gu, Caglar Gulcehre, Tom Le Paine +2

Gating mechanisms are widely used in neural network models, where they allow gradients to backpropagate more easily through depth or time. However, their saturation property introd…

cs.LG2019

Meta-Learning with Warped Gradient Descent

Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu +3

Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning. Typically, previous works…

stat.ML201957 cited

Task Agnostic Continual Learning via Meta Learning

Xu He, Jakub Sygnowski, Alexandre Galashov +3

While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that stud…

cs.LG201924 cited

Information asymmetry in KL-regularized RL

Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever +7

Many real world tasks exhibit rich structure that is repeated across different parts of the state space or in time. In this work we study the possibility of leveraging such repeate…