A
Anirudh Goyal
Researcher at Université de Montréal
Publications - 102
Citations - 4077
Anirudh Goyal is an academic researcher from Université de Montréal. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 22, co-authored 81 publications receiving 2626 citations.
Papers
More filters
Journal ArticleDOI
Toward Causal Representation Learning
Bernhard Schölkopf,Francesco Locatello,Stefan Bauer,Nan Rosemary Ke,Nal Kalchbrenner,Anirudh Goyal,Yoshua Bengio +6 more
TL;DR: The authors reviewed fundamental concepts of causal inference and related them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research.
Posted Content
Professor Forcing: A New Algorithm for Training Recurrent Networks
TL;DR: The Professor Forcing algorithm, which uses adversarial domain adaptation to encourage the dynamics of the recurrent network to be the same when training the network and when sampling from the network over multiple time steps, is introduced.
Posted Content
An Actor-Critic Algorithm for Sequence Prediction
Dzmitry Bahdanau,Philemon Brakel,Kelvin Xu,Anirudh Goyal,Ryan Lowe,Joelle Pineau,Aaron Courville,Yoshua Bengio +7 more
TL;DR: The authors proposed an actor-critic network that is trained to predict the value of an output token, given the policy of an actor network, which leads to improved performance on both a synthetic task and for German-English machine translation.
Proceedings Article
Professor Forcing: A New Algorithm for Training Recurrent Networks
TL;DR: In this article, the authors introduce the Professor Forcing algorithm, which uses adversarial domain adaptation to encourage the dynamics of the recurrent network to be the same when training the network and when sampling from the network over multiple time steps.
Posted Content
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
David Krueger,Tegan Maharaj,János Kramár,Mohammad Pezeshki,Nicolas Ballas,Nan Rosemary Ke,Anirudh Goyal,Yoshua Bengio,Aaron Courville,Chris Pal +9 more
TL;DR: This work proposes zoneout, a novel method for regularizing RNNs that uses random noise to train a pseudo-ensemble, improving generalization and performs an empirical investigation of various RNN regularizers, and finds that zoneout gives significant performance improvements across tasks.