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 Aleksandar Botev

SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision

Nov 10, 2021
Irina Higgins, Peter Wirnsberger, Andrew Jaegle, Aleksandar Botev

  Access Paper or Ask Questions

Which priors matter? Benchmarking models for learning latent dynamics

Nov 09, 2021
Aleksandar Botev, Andrew Jaegle, Peter Wirnsberger, Daniel Hennes, Irina Higgins

  Access Paper or Ask Questions

Better, Faster Fermionic Neural Networks

Nov 13, 2020
James S. Spencer, David Pfau, Aleksandar Botev, W. M. C. Foulkes

* To appear at the 3rd NeurIPS Workshop on Machine Learning and Physical Science 

  Access Paper or Ask Questions

Disentangling by Subspace Diffusion

Jun 23, 2020
David Pfau, Irina Higgins, Aleksandar Botev, Sébastien Racanière

* 21 pages, 13 figures 

  Access Paper or Ask Questions

Hamiltonian Generative Networks

Sep 30, 2019
Peter Toth, Danilo Jimenez Rezende, Andrew Jaegle, Sébastien Racanière, Aleksandar Botev, Irina Higgins

  Access Paper or Ask Questions

Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting

May 20, 2018
Hippolyt Ritter, Aleksandar Botev, David Barber

* 13 pages, 6 figures 

  Access Paper or Ask Questions

Practical Gauss-Newton Optimisation for Deep Learning

Jun 13, 2017
Aleksandar Botev, Hippolyt Ritter, David Barber

* ICML 2017 

  Access Paper or Ask Questions

Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent

Jul 11, 2016
Aleksandar Botev, Guy Lever, David Barber

  Access Paper or Ask Questions

Dealing with a large number of classes -- Likelihood, Discrimination or Ranking?

Jul 07, 2016
David Barber, Aleksandar Botev

  Access Paper or Ask Questions