Check out our virtual presentation for ICRA 2020! Video: youtu.be/tkF4wNfjzBI ArXiv: arxiv.org/abs/1910.06750 We've developed a realistic GAN-based simulator for extremely high-dimensional sonar images! #ICRA2020 #ICRA SeeByte Machine Intelligence Group @ Edinburgh

"Discriminative" semi-supervised learning makes use of the distribution over labels. We use a normalising flow to learn that distribution for arbitrarily complex labels: from one-hot vectors to binary vectors and images. Work with Carl Allen & Timothy Hospedales. arxiv.org/pdf/2007.02745…

First blog post on our latest model, the NewtonianVAE: jaques.xyz/newtonianvae/ Feedback welcome!

Recorded a small video presenting our @OCEANS2020 paper on generating images of any chosen resolution with R2D2-GANs. Video: youtu.be/fTaZPOXtVXI Paper: arxiv.org/abs/2003.01063 Machine Intelligence Group @ Edinburgh SeeByte #GANs #Sonar WiRE #WomenInSTEM

Delighted to brag - my paper 𝗨𝗻𝗹𝗶𝗺𝗶𝘁𝗲𝗱 𝗥𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻 𝗜𝗺𝗮𝗴𝗲 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗥𝟮𝗗𝟮-𝗚𝗔𝗡𝘀, won 1st prize in SPC OCEANS Conference. ArXiv: lnkd.in/daQhjGs Video: lnkd.in/d6_u6FY #GAN #WomenInSTEM Machine Intelligence Group @ Edinburgh SeeByte @InfAtEd

Little is known of the latent semantic structure learned by knowledge graph representation models. We address this by drawing a connection to word embeddings in recent work (w/ Carl Allen & Timothy Hospedales, to appear #ICLR2021). 1/4 openreview.net/forum?id=gLWj2…

Good news everyone: my paper (w/ Timothy Hospedales & Massi Pontil) on regularisation during fine-tuning has been accepted to #ICLR2021! Now I, too, will know the bittersweet experience of presenting at a virtual poster session! openreview.net/forum?id=IFqrg…

Spreading the word: Consider submitting to ICRA'21 workshop on Learning to Learn for Robotics (sites.google.com/view/learn-to-…) thanks to @yadrimz Franziska Meier Sarah Yevgen Chebotar and Timothy for organizing! Deadline is May 15.

At ICLR? Interested in meta-learning? Come check out the WS on Learning to Learn tomorrow (Fri 6 May). I'll be giving a semi-contrarian talk about freeing our meta-learning algorithms from preconceived notions of what meta-learning is or should be. iclr.cc/virtual/2021/w…

How Well Do Self-Supervised Models Transfer? Find out in our #CVPR presentation! Come chat with us in session 4 on Tuesday (11am EDT). Work done with Henry Gouk & Timothy Hospedales. Paper: arxiv.org/abs/2011.13377. Video: youtu.be/prZiTphuzO0. #CVPR2021 (1/n)

I passed my PhD viva today with no corrections! 🥳 🥳 🥳 Many thanks to my examiners Tim Rocktäschel and Mark Steedman for the very interesting and insightful discussion as a great way to finish my PhD @InfAtEd. Really excited to start @DeepMind on Monday! 😊

Congratulations Henry Gouk!

Happy to announce that I've been awarded a #RAEngResearch Fellowship for 2022! Over the next 5 years I'll be working on making machine learning reliable for problems with very little data. Thanks to @InfAtEd The University of Edinburgh Timothy Hospedales for the support!

Wondering about state of the art in algorithmic fairness and bias in AI? Yongshuo Zong' benchmark suite evaluates algorithms comprehensively across medical AI tasks. Bias is pervasive and fairness is hard to find. Paper & Code: ys-zong.github.io/MEDFAIR/

My Lab at Samsung AI Research Cambridge is #hiring research scientist and ML research engineer positions. Skilled in meta-learning, neuro-symbolic, foundation models, vision and language, robot learning, on-device learning? Apply online sec.wd3.myworkdayjobs.com/Samsung_Careers #MachineLearning

We are organizing the Universal Representations for Computer Vision Workshop at #BMVC2022 on Nov. 24th in London. We have a fantastic set of speakers! sites.google.com/view/universal…… We invite submissions of regular and short papers (See Call for Paper for more details).

Hello, everyone! We will be organizing an online workshop at ICLR 2023 aimed at one question: What do we need for successful domain generalization? The workshop will include invited talks from David Lopez-Paz, Amos Storkey, Tatiana, and Lequan Yu 1/2

The panel discussion for our #ICLR2023 workshop on Domain Generalisation starts in 45 minutes! Join us to hear what some leading researchers (Zachary Lipton, Boqing Gong, Qi Dou, etc) looking at robustness to distribution shift think about what we need. iclr.cc/virtual/2023/w…

Inspired by all the data and compute hungry advances recently, we're hosting a workshop on Affordable #MachineLearning at @InfAtEd on June 30th. Come along for a mix of invited talks, posters (submit one!), and more. Details here: bayeswatch.com/affordable_ml/