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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Joost van Amersfoort

Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective


Jun 17, 2021
Lewis Smith, Joost van Amersfoort, Haiwen Huang, Stephen Roberts, Yarin Gal

* Main paper 10 pages including references, appendix 10 pages. 7 figures and 6 tables including appendix 

  Access Paper or Ask Questions

Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty


Feb 23, 2021
Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal


  Access Paper or Ask Questions

Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression


Feb 22, 2021
Joost van Amersfoort, Lewis Smith, Andrew Jesson, Oscar Key, Yarin Gal


  Access Paper or Ask Questions

Single Shot Structured Pruning Before Training


Jul 01, 2020
Joost van Amersfoort, Milad Alizadeh, Sebastian Farquhar, Nicholas Lane, Yarin Gal


  Access Paper or Ask Questions

Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network


Mar 04, 2020
Joost van Amersfoort, Lewis Smith, Yee Whye Teh, Yarin Gal


  Access Paper or Ask Questions

BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning


Jun 19, 2019
Andreas Kirsch, Joost van Amersfoort, Yarin Gal


  Access Paper or Ask Questions

Deep Hashing using Entropy Regularised Product Quantisation Network


Feb 11, 2019
Jo Schlemper, Jose Caballero, Andy Aitken, Joost van Amersfoort


  Access Paper or Ask Questions

Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks


Nov 16, 2017
Joost van Amersfoort, Wenzhe Shi, Alejandro Acosta, Francisco Massa, Johannes Totz, Zehan Wang, Jose Caballero


  Access Paper or Ask Questions

Transformation-Based Models of Video Sequences


Apr 24, 2017
Joost van Amersfoort, Anitha Kannan, Marc'Aurelio Ranzato, Arthur Szlam, Du Tran, Soumith Chintala


  Access Paper or Ask Questions