Publications (45)
On the number of response regions of deep feed forward networks with piece-wise linear activations
Razvan Pascanu, Guido Montufar, Yoshua Bengio
On the saddle point problem for non-convex optimization
Razvan Pascanu, Yann N. Dauphin, Surya Ganguli +1
Progress & Compress: A scalable framework for continual learning
Jonathan Schwarz, Jelena Luketina, Wojciech M. Czarnecki +4
Policy Distillation
Andrei A. Rusu, Sergio Gomez Colmenarejo, Caglar Gulcehre +6
Memory-based Parameter Adaptation
Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae +7
A simple neural network module for relational reasoning
Adam Santoro, David Raposo, David G. T. Barrett +4
Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks
Caglar Gulcehre, Kyunghyun Cho, Razvan Pascanu +1
Relational inductive biases, deep learning, and graph networks
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst +24
Sobolev Training for Neural Networks
Wojciech Marian Czarnecki, Simon Osindero, Max Jaderberg +2
Information asymmetry in KL-regularized RL
Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever +7
Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery
Thomas Stepleton, Razvan Pascanu, Will Dabney +3
Advances in Optimizing Recurrent Networks
Yoshua Bengio, Nicolas Boulanger-Lewandowski, Razvan Pascanu
Imagination-Augmented Agents for Deep Reinforcement Learning
Théophane Weber, Sébastien Racanière, David P. Reichert +12
Theano: new features and speed improvements
Frédéric Bastien, Pascal Lamblin, Razvan Pascanu +6
Sim-to-Real Robot Learning from Pixels with Progressive Nets
Andrei A. Rusu, Mel Vecerik, Thomas Rothörl +3
Been There, Done That: Meta-Learning with Episodic Recall
Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson +4
Distilling Policy Distillation
Wojciech Marian Czarnecki, Razvan Pascanu, Simon Osindero +3
Model compression via distillation and quantization
Antonio Polino, Razvan Pascanu, Dan Alistarh
Ray Interference: a Source of Plateaus in Deep Reinforcement Learning
Tom Schaul, Diana Borsa, Joseph Modayil +1
Interaction Networks for Learning about Objects, Relations and Physics
Peter W. Battaglia, Razvan Pascanu, Matthew Lai +2
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain +110
Hyperbolic Attention Networks
Caglar Gulcehre, Misha Denil, Mateusz Malinowski +8
Deep Self-Taught Learning for Handwritten Character Recognition
Frédéric Bastien, Yoshua Bengio, Arnaud Bergeron +14
Learning model-based planning from scratch
Razvan Pascanu, Yujia Li, Oriol Vinyals +7
Visual Interaction Networks
Nicholas Watters, Andrea Tacchetti, Theophane Weber +3
Relational Deep Reinforcement Learning
Vinicius Zambaldi, David Raposo, Adam Santoro +13
Sharp Minima Can Generalize For Deep Nets
Laurent Dinh, Razvan Pascanu, Samy Bengio +1
Pylearn2: a machine learning research library
Ian J. Goodfellow, David Warde-Farley, Pascal Lamblin +6
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
Yann Dauphin, Razvan Pascanu, Caglar Gulcehre +3
Meta-Learning with Latent Embedding Optimization
Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski +4
Relational recurrent neural networks
Adam Santoro, Ryan Faulkner, David Raposo +7
Task Agnostic Continual Learning via Meta Learning
Xu He, Jakub Sygnowski, Alexandre Galashov +3
Discovering objects and their relations from entangled scene representations
David Raposo, Adam Santoro, David Barrett +3
Autotagging music with conditional restricted Boltzmann machines
Michael Mandel, Razvan Pascanu, Hugo Larochelle +1
On the Number of Linear Regions of Deep Neural Networks
Guido Montúfar, Razvan Pascanu, Kyunghyun Cho +1
Local minima in training of neural networks
Grzegorz Swirszcz, Wojciech Marian Czarnecki, Razvan Pascanu
Natural Neural Networks
Guillaume Desjardins, Karen Simonyan, Razvan Pascanu +1
Distral: Robust Multitask Reinforcement Learning
Yee Whye Teh, Victor Bapst, Wojciech Marian Czarnecki +5
On the difficulty of training Recurrent Neural Networks
Razvan Pascanu, Tomas Mikolov, Yoshua Bengio
Learning Deep Generative Models of Graphs
Yujia Li, Oriol Vinyals, Chris Dyer +2
Meta-learning of Sequential Strategies
Pedro A. Ortega, Jane X. Wang, Mark Rowland +21
Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines
Guillaume Desjardins, Razvan Pascanu, Aaron Courville +1
Mix&Match - Agent Curricula for Reinforcement Learning
Wojciech Marian Czarnecki, Siddhant M. Jayakumar, Max Jaderberg +5
Learning to Navigate in Complex Environments
Piotr Mirowski, Razvan Pascanu, Fabio Viola +9
How to Construct Deep Recurrent Neural Networks
Razvan Pascanu, Caglar Gulcehre, Kyunghyun Cho +1