Timezone: »
We introduce Natural Neural Networks, a novel family of algorithms that speed up convergence by adapting their internal representation during training to improve conditioning of the Fisher matrix. In particular, we show a specific example that employs a simple and efficient reparametrization of the neural network weights by implicitly whitening the representation obtained at each layer, while preserving the feed-forward computation of the network. Such networks can be trained efficiently via the proposed Projected Natural Gradient Descent algorithm (PRONG), which amortizes the cost of these reparametrizations over many parameter updates and is closely related to the Mirror Descent online learning algorithm. We highlight the benefits of our method on both unsupervised and supervised learning tasks, and showcase its scalability by training on the large-scale ImageNet Challenge dataset.
Author Information
Guillaume Desjardins (Google DeepMind)
Karen Simonyan (Google DeepMind)
Razvan Pascanu (Google DeepMind)
koray kavukcuoglu (Google DeepMind)
More from the Same Authors
-
2021 : LiRo: Benchmark and leaderboard for Romanian language tasks »
Stefan Dumitrescu · Petru Rebeja · Beata Lorincz · Mihaela Petruta Gaman · Andrei Avram · Mihai Ilie · Andrei Pruteanu · Adriana Stan · Lorena Rosia · Cristina Iacobescu · Luciana Morogan · George Dima · Gabriel Marchidan · Traian Rebedea · Madalina Chitez · Dani Yogatama · Sebastian Ruder · Radu Tudor Ionescu · Razvan Pascanu · Viorica Patraucean -
2021 Spotlight: Reward is enough for convex MDPs »
Tom Zahavy · Brendan O'Donoghue · Guillaume Desjardins · Satinder Singh -
2022 : Pre-training via Denoising for Molecular Property Prediction »
Sheheryar Zaidi · Michael Schaarschmidt · James Martens · Hyunjik Kim · Yee Whye Teh · Alvaro Sanchez Gonzalez · Peter Battaglia · Razvan Pascanu · Jonathan Godwin -
2022 : When Does Re-initialization Work? »
Sheheryar Zaidi · Tudor Berariu · Hyunjik Kim · Jorg Bornschein · Claudia Clopath · Yee Whye Teh · Razvan Pascanu -
2023 : Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models »
Amal Rannen-Triki · Jorg Bornschein · Razvan Pascanu · Alexandre Galashov · Michalis Titsias · Marcus Hutter · András György · Yee Whye Teh -
2023 : Stochastic linear dynamics in parameters to deal with Neural Networks plasticity loss »
Alexandre Galashov · Michalis Titsias · Razvan Pascanu · Yee Whye Teh · Maneesh Sahani -
2023 Poster: The Tunnel Effect: Building Data Representations in Deep Neural Networks »
Wojciech Masarczyk · Mateusz Ostaszewski · Ehsan Imani · Razvan Pascanu · Piotr Miłoś · Tomasz Trzcinski -
2023 Poster: Deep Reinforcement Learning with Plasticity Injection »
Evgenii Nikishin · Junhyuk Oh · Georg Ostrovski · Clare Lyle · Razvan Pascanu · Will Dabney · Andre Barreto -
2023 Poster: Learning to Modulate pre-trained Models in RL »
Thomas Schmied · Markus Hofmarcher · Fabian Paischer · Razvan Pascanu · Sepp Hochreiter -
2022 Poster: Disentangling Transfer in Continual Reinforcement Learning »
Maciej Wolczyk · Michał Zając · Razvan Pascanu · Łukasz Kuciński · Piotr Miłoś -
2021 Poster: Entropic Desired Dynamics for Intrinsic Control »
Steven Hansen · Guillaume Desjardins · Kate Baumli · David Warde-Farley · Nicolas Heess · Simon Osindero · Volodymyr Mnih -
2021 Poster: Reward is enough for convex MDPs »
Tom Zahavy · Brendan O'Donoghue · Guillaume Desjardins · Satinder Singh -
2021 Poster: Powerpropagation: A sparsity inducing weight reparameterisation »
Jonathan Richard Schwarz · Siddhant Jayakumar · Razvan Pascanu · Peter E Latham · Yee Teh -
2021 Poster: Continual World: A Robotic Benchmark For Continual Reinforcement Learning »
Maciej Wołczyk · Michał Zając · Razvan Pascanu · Łukasz Kuciński · Piotr Miłoś -
2021 Poster: On the Role of Optimization in Double Descent: A Least Squares Study »
Ilja Kuzborskij · Csaba Szepesvari · Omar Rivasplata · Amal Rannen-Triki · Razvan Pascanu -
2020 Poster: Evolving Normalization-Activation Layers »
Hanxiao Liu · Andy Brock · Karen Simonyan · Quoc V Le -
2020 Poster: Top-KAST: Top-K Always Sparse Training »
Siddhant Jayakumar · Razvan Pascanu · Jack Rae · Simon Osindero · Erich Elsen -
2020 Spotlight: Evolving Normalization-Activation Layers »
Hanxiao Liu · Andy Brock · Karen Simonyan · Quoc V Le -
2020 Poster: Pointer Graph Networks »
Petar Veličković · Lars Buesing · Matthew Overlan · Razvan Pascanu · Oriol Vinyals · Charles Blundell -
2020 Poster: Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning »
Jean-Bastien Grill · Florian Strub · Florent Altché · Corentin Tallec · Pierre Richemond · Elena Buchatskaya · Carl Doersch · Bernardo Avila Pires · Daniel (Zhaohan) Guo · Mohammad Gheshlaghi Azar · Bilal Piot · koray kavukcuoglu · Remi Munos · Michal Valko -
2020 Spotlight: Pointer Graph Networks »
Petar Veličković · Lars Buesing · Matthew Overlan · Razvan Pascanu · Oriol Vinyals · Charles Blundell -
2020 Oral: Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning »
Jean-Bastien Grill · Florian Strub · Florent Altché · Corentin Tallec · Pierre Richemond · Elena Buchatskaya · Carl Doersch · Bernardo Avila Pires · Daniel (Zhaohan) Guo · Mohammad Gheshlaghi Azar · Bilal Piot · koray kavukcuoglu · Remi Munos · Michal Valko -
2020 Poster: Understanding the Role of Training Regimes in Continual Learning »
Seyed Iman Mirzadeh · Mehrdad Farajtabar · Razvan Pascanu · Hassan Ghasemzadeh -
2019 Poster: Large Scale Adversarial Representation Learning »
Jeff Donahue · Karen Simonyan -
2019 Poster: Continual Unsupervised Representation Learning »
Dushyant Rao · Francesco Visin · Andrei A Rusu · Razvan Pascanu · Yee Whye Teh · Raia Hadsell -
2018 : Introduction of the workshop »
Razvan Pascanu · Yee Teh · Mark Ring · Marc Pickett -
2018 Workshop: Continual Learning »
Razvan Pascanu · Yee Teh · Marc Pickett · Mark Ring -
2018 Poster: Learning to Navigate in Cities Without a Map »
Piotr Mirowski · Matt Grimes · Mateusz Malinowski · Karl Moritz Hermann · Keith Anderson · Denis Teplyashin · Karen Simonyan · koray kavukcuoglu · Andrew Zisserman · Raia Hadsell -
2018 Poster: The challenge of realistic music generation: modelling raw audio at scale »
Sander Dieleman · Aaron van den Oord · Karen Simonyan -
2018 Poster: Relational recurrent neural networks »
Adam Santoro · Ryan Faulkner · David Raposo · Jack Rae · Mike Chrzanowski · Theophane Weber · Daan Wierstra · Oriol Vinyals · Razvan Pascanu · Timothy Lillicrap -
2017 Poster: Distral: Robust multitask reinforcement learning »
Yee Teh · Victor Bapst · Wojciech Czarnecki · John Quan · James Kirkpatrick · Raia Hadsell · Nicolas Heess · Razvan Pascanu -
2017 Poster: A simple neural network module for relational reasoning »
Adam Santoro · David Raposo · David Barrett · Mateusz Malinowski · Razvan Pascanu · Peter Battaglia · Timothy Lillicrap -
2017 Poster: Imagination-Augmented Agents for Deep Reinforcement Learning »
Sébastien Racanière · Theophane Weber · David Reichert · Lars Buesing · Arthur Guez · Danilo Jimenez Rezende · Adrià Puigdomènech Badia · Oriol Vinyals · Nicolas Heess · Yujia Li · Razvan Pascanu · Peter Battaglia · Demis Hassabis · David Silver · Daan Wierstra -
2017 Spotlight: A simple neural network module for relational reasoning »
Adam Santoro · David Raposo · David Barrett · Mateusz Malinowski · Razvan Pascanu · Peter Battaglia · Timothy Lillicrap -
2017 Oral: Imagination-Augmented Agents for Deep Reinforcement Learning »
Sébastien Racanière · Theophane Weber · David Reichert · Lars Buesing · Arthur Guez · Danilo Jimenez Rezende · Adrià Puigdomènech Badia · Oriol Vinyals · Nicolas Heess · Yujia Li · Razvan Pascanu · Peter Battaglia · Demis Hassabis · David Silver · Daan Wierstra -
2017 Poster: Visual Interaction Networks: Learning a Physics Simulator from Video »
Nicholas Watters · Daniel Zoran · Theophane Weber · Peter Battaglia · Razvan Pascanu · Andrea Tacchetti -
2017 Poster: Neural Discrete Representation Learning »
Aaron van den Oord · Oriol Vinyals · koray kavukcuoglu -
2017 Poster: Sobolev Training for Neural Networks »
Wojciech Czarnecki · Simon Osindero · Max Jaderberg · Grzegorz Swirszcz · Razvan Pascanu -
2016 Workshop: Continual Learning and Deep Networks »
Razvan Pascanu · Mark Ring · Tom Schaul -
2016 Poster: Conditional Image Generation with PixelCNN Decoders »
Aaron van den Oord · Nal Kalchbrenner · Lasse Espeholt · koray kavukcuoglu · Oriol Vinyals · Alex Graves -
2016 Poster: Attend, Infer, Repeat: Fast Scene Understanding with Generative Models »
S. M. Ali Eslami · Nicolas Heess · Theophane Weber · Yuval Tassa · David Szepesvari · koray kavukcuoglu · Geoffrey E Hinton -
2016 Poster: Interaction Networks for Learning about Objects, Relations and Physics »
Peter Battaglia · Razvan Pascanu · Matthew Lai · Danilo Jimenez Rezende · koray kavukcuoglu -
2016 Poster: Strategic Attentive Writer for Learning Macro-Actions »
Alexander (Sasha) Vezhnevets · Volodymyr Mnih · Simon Osindero · Alex Graves · Oriol Vinyals · John Agapiou · koray kavukcuoglu -
2016 Poster: Matching Networks for One Shot Learning »
Oriol Vinyals · Charles Blundell · Timothy Lillicrap · koray kavukcuoglu · Daan Wierstra -
2015 Poster: Spatial Transformer Networks »
Max Jaderberg · Karen Simonyan · Andrew Zisserman · koray kavukcuoglu -
2015 Spotlight: Spatial Transformer Networks »
Max Jaderberg · Karen Simonyan · Andrew Zisserman · koray kavukcuoglu -
2014 Poster: Recurrent Models of Visual Attention »
Volodymyr Mnih · Nicolas Heess · Alex Graves · koray kavukcuoglu -
2014 Spotlight: Recurrent Models of Visual Attention »
Volodymyr Mnih · Nicolas Heess · Alex Graves · koray kavukcuoglu -
2014 Poster: Identifying and attacking the saddle point problem in high-dimensional non-convex optimization »
Yann N Dauphin · Razvan Pascanu · Caglar Gulcehre · Kyunghyun Cho · Surya Ganguli · Yoshua Bengio -
2014 Poster: Two-Stream Convolutional Networks for Action Recognition in Videos »
Karen Simonyan · Andrew Zisserman -
2014 Poster: On the Number of Linear Regions of Deep Neural Networks »
Guido F Montufar · Razvan Pascanu · Kyunghyun Cho · Yoshua Bengio -
2014 Spotlight: Two-Stream Convolutional Networks for Action Recognition in Videos »
Karen Simonyan · Andrew Zisserman -
2013 Poster: Deep Fisher Networks for Large-Scale Image Classification »
Karen Simonyan · Andrea Vedaldi · Andrew Zisserman -
2013 Spotlight: Deep Fisher Networks for Large-Scale Image Classification »
Karen Simonyan · Andrea Vedaldi · Andrew Zisserman -
2012 Poster: Learning the Dependency Structure of Latent Factors »
Yunlong He · Yanjun Qi · koray kavukcuoglu · Haesun Park -
2010 Spotlight: Learning Convolutional Feature Hierarchies for Visual Recognition »
koray kavukcuoglu · Pierre Sermanet · Y-Lan Boureau · Karol Gregor · Michael Mathieu · Yann LeCun -
2010 Poster: Learning Convolutional Feature Hierarchies for Visual Recognition »
koray kavukcuoglu · Pierre Sermanet · Y-Lan Boureau · Karol Gregor · Michael Mathieu · Yann LeCun