Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Constellation: Learning relational abstractions over objects for compositional imagination


Jul 23, 2021
James C. R. Whittington, Rishabh Kabra, Loic Matthey, Christopher P. Burgess, Alexander Lerchner


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Reasoning-Modulated Representations


Jul 19, 2021
Petar Veličković, Matko Bošnjak, Thomas Kipf, Alexander Lerchner, Raia Hadsell, Razvan Pascanu, Charles Blundell

* ICML 2021 Workshop on Self-Supervised Learning for Reasoning and Perception (Spotlight Talk). 7 pages, 3 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition


Jun 07, 2021
Rishabh Kabra, Daniel Zoran, Goker Erdogan, Loic Matthey, Antonia Creswell, Matthew Botvinick, Alexander Lerchner, Christopher P. Burgess

* Animated figures are available at https://sites.google.com/view/simone-scene-understanding/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Alchemy: A structured task distribution for meta-reinforcement learning


Feb 04, 2021
Jane X. Wang, Michael King, Nicolas Porcel, Zeb Kurth-Nelson, Tina Zhu, Charlie Deck, Peter Choy, Mary Cassin, Malcolm Reynolds, Francis Song, Gavin Buttimore, David P. Reichert, Neil Rabinowitz, Loic Matthey, Demis Hassabis, Alexander Lerchner, Matthew Botvinick

* 16 pages, 9 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Formalising Concepts as Grounded Abstractions


Jan 13, 2021
Stephen Clark, Alexander Lerchner, Tamara von Glehn, Olivier Tieleman, Richard Tanburn, Misha Dashevskiy, Matko Bosnjak


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Heuristic for Unsupervised Model Selection for Variational Disentangled Representation Learning


May 29, 2019
Sunny Duan, Nicholas Watters, Loic Matthey, Christopher P. Burgess, Alexander Lerchner, Irina Higgins


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration


May 22, 2019
Nicholas Watters, Loic Matthey, Matko Bosnjak, Christopher P. Burgess, Alexander Lerchner


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-Object Representation Learning with Iterative Variational Inference


Mar 01, 2019
Klaus Greff, Raphaël Lopez Kaufmann, Rishab Kabra, Nick Watters, Chris Burgess, Daniel Zoran, Loic Matthey, Matthew Botvinick, Alexander Lerchner


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

MONet: Unsupervised Scene Decomposition and Representation


Jan 22, 2019
Christopher P. Burgess, Loic Matthey, Nicholas Watters, Rishabh Kabra, Irina Higgins, Matt Botvinick, Alexander Lerchner


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs


Jan 21, 2019
Nicholas Watters, Loic Matthey, Christopher P. Burgess, Alexander Lerchner


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>