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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Know your audience: specializing grounded language models with the game of Dixit


Jun 16, 2022
Aaditya K. Singh, David Ding, Andrew Saxe, Felix Hill, Andrew K. Lampinen

* 27 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

Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation


May 18, 2022
Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath, Sebastian Goldt, Andrew Saxe


   Access Paper or Ask Questions

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

Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals


Mar 22, 2022
Timo Flesch, David G. Nagy, Andrew Saxe, Christopher Summerfield

* 29 pages, 7 figures 

   Access Paper or Ask Questions

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

Continual Learning in the Teacher-Student Setup: Impact of Task Similarity


Jul 09, 2021
Sebastian Lee, Sebastian Goldt, Andrew Saxe

* Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6109-6119, 2021 

   Access Paper or Ask Questions

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

An Analytical Theory of Curriculum Learning in Teacher-Student Networks


Jun 15, 2021
Luca Saglietti, Stefano Sarao Mannelli, Andrew Saxe

* 10 pages + appendix 

   Access Paper or Ask Questions

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

Probing transfer learning with a model of synthetic correlated datasets


Jun 09, 2021
Federica Gerace, Luca Saglietti, Stefano Sarao Mannelli, Andrew Saxe, Lenka Zdeborová


   Access Paper or Ask Questions

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

Are Efficient Deep Representations Learnable?


Jul 17, 2018
Maxwell Nye, Andrew Saxe

* Presented at ICLR 2018 Workshop 

   Access Paper or Ask Questions

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

Tensor Switching Networks


Oct 31, 2016
Chuan-Yung Tsai, Andrew Saxe, David Cox


   Access Paper or Ask Questions

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