OATML | Oxford Applied and Theoretical Machine Learning Group

Oxford Applied and Theoretical Machine Learning Group

Pragmatic Approaches to Fundamental Research

Oxford Applied and Theoretical Machine Learning Group

Pragmatic Approaches to Fundamental Research

Oxford Applied and Theoretical Machine Learning Group

Pragmatic Approaches to Fundamental Research

Oxford Applied and Theoretical Machine Learning Group

Pragmatic Approaches to Fundamental Research

Oxford Applied and Theoretical Machine Learning Group

Pragmatic Approaches to Fundamental Research

Oxford Applied and Theoretical Machine Learning Group

Pragmatic Approaches to Fundamental Research

Oxford Applied and Theoretical Machine Learning Group

Pragmatic Approaches to Fundamental Research

Oxford Applied and Theoretical Machine Learning Group

Pragmatic Approaches to Fundamental Research

News

Two OATML students received ICML 2019 Outstanding Reviewer Awards

02 Jun 2019

OATML DPhil students Lewis Smith and Tim G. J. Rudner received ICML 2019 Outstanding Reviewer Awards (top 5% of reviewers).

Yarin Gal to speak at the European Space Agency

01 Jun 2019

Prof Yarin Gal will be speaking at the European Space Agency’s Phi-week, discussing work done at OATML on AI in space. The talk will cover work on topics ranging from exoplanet atmospheric retrieval to asteroid shape modelling from radar data.

Angelos Filos' paper accepted for oral presentation at ICML 2019 Workshop

15 May 2019

OATML graduate student Angelos Filos will present his paper ‘Inverse Reinforcement Learning for Limit Order Book Dynamics’ at the the ICML 2019 Workshop on Applications and Infrastructure for Multi-Agent Learning, with the paper selected for an oral presentation.

Yarin Gal to speak at the Royal Society's Summer Science Exhibition on AI and Art

02 May 2019

Prof Yarin Gal will be speaking at the Royal Society’s Summer Science Exhibition on 6 July, discussing work on AI and art. The talk will cover techniques in machine learning that give us the chance to venture beyond the frame of some famous paintings.

More news

Publications

We do research in both theoretical machine learning, as well as applications of machine learning in various domains, including medical, astronomy, autonomous driving, and more.

Recent publications:

	07/2019: "Benchmarking Bayesian Deep Learning with Diabetic Retinopathy Diagnosis" (Angelos Filos, Sebastian Farquhar, Aidan Gomez, Tim G. J. Rudner, Zac Kenton, Lewis Smith, Milad Alizadeh, Arnoud de Kroon, Yarin Gal).
	05/2019: "BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning" (Andreas Kirsch, Joost van Amersfoort, Yarin Gal).
	05/2019: "Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning" (Mike Walmsley, Lewis Smith, Chris Lintott, Yarin Gal, Steven Bamford, Hugh Dickinson, Lucy Fortson, Sandor Kruk, Karen Masters, Claudia Scarlata, Brooke Simmons, Rebecca Smethurst, Darryl Wright).

Reproducibility and Code

One of our lab's missions is to contribute to the reproducibility effort. Here we provide code for our own research, as well as reproductions of works by others (e.g. ones we implemented as baselines as part of our own research).

Recent code release:

	07/2019: Putting TensorFlow back in PyTorch, back in TensorFlow (differentiable TensorFlow PyTorch adapters) (Andreas Kirsch).
	06/2019: Code for BatchBALD blog post and paper (active learning) (Andreas Kirsch, Joost van Amersfoort, Yarin Gal).
	06/2019: Reproducing the results from "Do Deep Generative Models Know What They Don't Know?" (Joost van Amersfoort).

Group Blog

Recent group blog posts:

	02 Jul 2019: Poor generalization can be dangerous in RL! (Zac Kenton, Angelos Filos, Yarin Gal)
	24 Jun 2019: Human in the Loop: Deep Learning without Wasteful Labelling (Andreas Kirsch, Joost van Amersfoort, Yarin Gal)
	14 Jun 2019: Bayesian Deep Learning Benchmarks (Angelos Filos, Sebastian Farquhar, Aidan Gomez, Tim G. J. Rudner, Zac Kenton, Lewis Smith, Milad Alizadeh, Yarin Gal)
	05 Jun 2019: Targeted Dropout (Aidan Gomez)

Group Members

We are researchers coming from varied backgrounds, including Computer Science, Maths & Stats, Engineering, and Physics.

We come from academia (Oxford, Cambridge, MILA, McGill, U of Amsterdam, U of Toronto, Yale, and others) and industry (Google, DeepMind, Twitter, Qualcomm, and startups).

We include 3 Rhodes Scholars, 2 Clarendon Scholars, one DeepMind Scholar, with our students funded by many additional sources (AIMS CDT, Cyber CDT, and more).

Contact

We are located at
Department of Computer Science, University of Oxford
Wolfson Building
Parks Road
OXFORD
OX1 3QD
UK

Twitter: @OATML_Oxford
Github: OATML
Email: oatml@cs.ox.ac.uk