user avatar
Yarin
@yaringal
Professor of Machine Learning, University of Oxford @OATML_Oxford Group Leader Expert Advisor to AISI "One of the top machine-learning people" - Tim Berners-Lee
Oxford, England
yarin.co
Joined February 2014
250
Following
43.3K
Followers
Posts
  • user avatar
    Yarin
    @yaringal
    Jun 14, 2019
    Really excited to release Bayesian Deep Learning Benchmarks - please share with others who you think might like this, and have a look at the blog/repo/colab: github.com/OATML/bdl-benc… This work was done over a period of a year and a half by many collaborators @OATML_Oxford
  • user avatar
    Yarin
    @yaringal
    Jan 23, 2024
    I'm hiring! I'm building 4 research groups under me at AISI (formerly the UK's Taskforce on Frontier AI) to work on foundational AI safety research. [1/5]
    gov.uk
    Introducing the AI Safety Institute
    159K
  • user avatar
    Yarin
    @yaringal
    Aug 31, 2019
    All the slides from my Bayesian Deep Learning tutorial at MLSS 2019 Moscow, including a practical in Active Learning with jupyter notebooks (practical credit: Ivan Nazarov), are now online bdl101.ml
  • user avatar
    Yarin
    @yaringal
    Oct 13, 2016
    New blog post! "Uncertainty in Deep Learning" - also my PhD thesis and lots of new results mlg.eng.cam.ac.uk/yarin/blog_224…
  • user avatar
    Yarin
    @yaringal
    Nov 30, 2019
    I really like blog posts which try to teach the reader old ideas. This one is about ways to visualise concepts in information theory, mentioned (cautiously) in solution 8.8 in Mackay's book (remember, positive areas can be negative quantities!) By @BlackHC
    blackhc.net
    Better intuition for information theory
    Better visual explanations of information theoretic quantities like entropy and mutual information using I-diagrams. Based on Raymond W. Yeung's "A new outlook on Shannon's information measures"...
  • user avatar
    Yarin
    @yaringal
    Mar 10, 2021
    Did you know that you can beat Deep Ensemble Uncertainty with a single deterministic net? We prove that softmax nets can't normally capture epistemic uncertainty, but with an appropriate inductive bias any pre-trained net can implicitly capture uncertainty arxiv.org/abs/2102.11582
  • user avatar
    Yarin
    @yaringal
    Nov 30, 2024
    I'm looking for PhD applicants who have expertise in Gaussian processes and/or Transformers for an exciting PhD project If this sounds interesting, application deadline for funding is 3/12 Please share with people you think this might be relevant to!
    How to Apply - OATML
    From oatml.cs.ox.ac.uk
    58K
  • user avatar
    Yarin
    @yaringal
    Nov 23, 2017
    Dear research community, please keep machine learning open access @NipsConference @icmlconf @iclr2017 JMLR
    nature.com
    Nature Machine Intelligence
    Nature Machine Intelligence will publish high-quality original research and reviews in a wide range of topics in machine learning, robotics and AI. The ...
  • user avatar
    Yarin
    @yaringal
    Dec 19, 2019
    Very happy to be named one of MIT Technology Review @techreview Europe's 35 under 35. Many thanks to all my collaborators over the years! innovatorsunder35.com/the-list/yarin…
  • user avatar
    Yarin
    @yaringal
    Oct 20, 2025
    We're looking for PhD students to join @OATML_Oxford! We work on topics such as developing Bayesian deep learning methodology, applications of ML, AI security, and understanding ML methodology. A fully funded scholarship opportunity to work with us:
    foaicdt.ox.ac.uk
    Home
    32K
  • user avatar
    Yarin
    @yaringal
    Sep 6, 2021
    This year's #BDL workshop at @NeurIPSConf will focus on the reliability of BDL in downstream tasks, with invited talks from practitioners and the two NeurIPS BDL challenges bayesiandeeplearning.org Please consider submitting extended abstracts by Oct 1, or posters by Dec 1
  • user avatar
    Yarin
    @yaringal
    Jul 11, 2020
    Our car below never saw roundabouts at training time. But using dropout ensembles' epistemic uncertainty we can choose the best worst-case plan to follow at deployment We put code online to make it as easy as MNIST to plug & play your own BDL tools: github.com/OATML/oatomobi…
    user avatar
    Yarin
    @yaringal
    Jul 10, 2020
    Can autonomous 🚘 identify, recover from, and adapt to distribution shifts? We play with BDL and robust control to get cars to recover&adapt when they don't know what to do At ICML with @filangelos @ptigas @rowantmc @nick_rhinehart @svlevine 📄🎞️🕸️💻: oatml.cs.ox.ac.uk/blog/2020/07/0…
  • user avatar
    Yarin
    @yaringal
    Nov 23, 2019
    The Bayesian Deep Learning workshop website has been updated with accepted papers and schedule #BDL2019 bayesiandeeplearning.org
  • user avatar
    Yarin
    @yaringal
    Mar 7, 2017
    Bayesian neural networks uncertainty can be used to distinguish adversarial from non-adversarial images! new results mlg.eng.cam.ac.uk/yarin/publicat…