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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Bounding generalization error with input compression: An empirical study with infinite-width networks


Jul 19, 2022
Angus Galloway, Anna Golubeva, Mahmoud Salem, Mihai Nica, Yani Ioannou, Graham W. Taylor

* 12 pages main content, 26 pages total 

   Access Paper or Ask Questions

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

Monitoring Shortcut Learning using Mutual Information


Jun 27, 2022
Mohammed Adnan, Yani Ioannou, Chuan-Yung Tsai, Angus Galloway, H. R. Tizhoosh, Graham W. Taylor

* Accepted at ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability 

   Access Paper or Ask Questions

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

Understanding the impact of image and input resolution on deep digital pathology patch classifiers


Apr 29, 2022
Eu Wern Teh, Graham W. Taylor

* To appear in the Conference on Computer and Robot Vision (CRV), 2022 

   Access Paper or Ask Questions

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

DeepRNG: Towards Deep Reinforcement Learning-Assisted Generative Testing of Software


Jan 29, 2022
Chuan-Yung Tsai, Graham W. Taylor

* Workshop on ML for Systems, 35th Conference on Neural Information Processing Systems (NeurIPS 2021) 

   Access Paper or Ask Questions

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

On Evaluation Metrics for Graph Generative Models


Jan 24, 2022
Rylee Thompson, Boris Knyazev, Elahe Ghalebi, Jungtaek Kim, Graham W. Taylor

* Published as a conference paper at ICLR 2022 

   Access Paper or Ask Questions

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

Learning with Less Labels in Digital Pathology via Scribble Supervision from Natural Images


Jan 20, 2022
Eu Wern Teh, Graham W. Taylor

* To appear in IEEE International Symposium on Biomedical Imaging (ISBI) 2022 

   Access Paper or Ask Questions

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

Learning with less labels in Digital Pathology via Scribble Supervision from natural images


Jan 07, 2022
Eu Wern Teh, Graham W. Taylor

* To appear in IEEE International Symposium on Biomedical Imaging (ISBI) 2022 

   Access Paper or Ask Questions

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

Domain-Agnostic Clustering with Self-Distillation


Nov 23, 2021
Mohammed Adnan, Yani A. Ioannou, Chuan-Yung Tsai, Graham W. Taylor

* NeurIPS 2021 Workshop: Self-Supervised Learning - Theory and Practice 

   Access Paper or Ask Questions

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

An Empirical Study of Neural Kernel Bandits


Nov 05, 2021
Michal Lisicki, Arash Afkanpour, Graham W. Taylor

* Presented at Workshop on Bayesian Deep Learning at NeurIPS 2021 

   Access Paper or Ask Questions

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

Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning


Oct 29, 2021
Hyunsoo Chung, Jungtaek Kim, Boris Knyazev, Jinhwi Lee, Graham W. Taylor, Jaesik Park, Minsu Cho

* 21 pages, 13 figures, 7 tables. Accepted at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021) 

   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
3
4
5
6
7
>>