🤖New blog post🤖 AlphaFold 2 refines protein structures in an iterative, equivariant way. @FabianFuchsML and I wrote about the challenges of building an iterative, equivariant SE(3)-Transformer. Complete with code and a tech report! https://t.co/L1waoO6ho8

I will be giving an overview of what we are up to @PrescientDesign during my talk @CCG_MOE #BiologicsByDesign2023 #proteinengineering #machinelearning #proteindesign

🕸️ In "Learnable Commutative Monoids for Graph Neural Networks", Euan Ong and I show how to build potent, learnable and aligned aggregators for GNNs, building on the success of PNA (@GabriCorso @dom_beaini) and set aggregation (@EdWagstaff @FabianFuchsML @martinengelcke).

📢 New blog post! Realising an intricate connection between PNA (@GabriCorso @lukecavabarrett @dom_beaini @pl219_Cambridge) & the seminal work on set representations (Wagstaff @FabianFuchsML @martinengelcke @IngmarPosner @maosbot), Fabian and I join forces to attempt to explain!

BayesOpt is great for exploring the unknown, but it's hard to know when you're accurately predicting new inputs. Two big reasons it's hard --- faulty assumptions and covariate shift. Our new preprint shows conformal prediction can improve coverage! https://t.co/kilh2hW9Jj 1/7

I've seen plenty of people flatly dismissing these sorts of concerns as "sci-fi", but no substantive arguments that they shouldn't be taken seriously. That's partly because I don't really know where to look for such arguments. Are there any?

It is w pride (and a tear in my eye) that after 6 months of competitive assessment, negotiations & legal due diligence, I can announce that @esa has awarded a €1M contract to a program I am leading in consortium with @CompSciOxford @isp_uv_es @BrockmannCon, project #OpenSR

I'm hiring for Research Scientist and Research Engineer roles on the Alignment team at DeepMind! Come talk to me at the EA Global London career fair (4-8 pm Friday 15 April), or DM / email me and I can let you know when the job ad officially goes up.

Graph neural networks often have to globally aggregate over all nodes. How we do this can have a significant impact on performance 🎯. After we recently finished a project on this, I wrote a blog post on this topic. Let me know what you think! :) ➡️ https://t.co/OGJJAF9w9C ☕️

Multiple open faculty positions at @CompSciOxford - join a great CS department! https://t.co/OuWjlNNc9j

I am looking for troublemakers who want to start a PhD in #probabilistic #ML #AI at @ancAtEd @InfAtEd @EdinburghUni to design the foundations for the next generations of #autonomous #systems. Drop me an email or DM here! Please share!

Sign up to join discussions on some very interesting topics! To name a couple: - “I wish I knew … at the start of my research career” - “Is deep learning the master algorithm?” This event is hosted as part of the social program at #NeurIPS2021 😎😎

This two-tweet thread may be the best thing I have ever seen written on the subject of i.i.d. coin flips.

A truly extraordinary footnote.

Playing around with @sportsracer48's new notebook. Taking advantage of the optical flow features and water drops. Wild! #VQGAN #vqganclip

Twitter, a favour. And yes, it's a pub not allowed to stay al fresco: The Ship Tavern in Holborn has been close to my heart for a while. It's a family-run pub in the middle of central London and it's been there since 1549. It also happens to be *beautiful*

I'm especially excited about potential use cases in healthcare. Here is an explanation of "how would this retinal image have to change in order for it to be considered diseased" --> shows that the disease classifier is detecting "clustered exudates" (the bright dots)

Germany, Japan, and Italy sharing the physics Nobel laureates this year. Gosh they make quite the team don’t they?

me: oh I should backup the wolfram cloud notebooks I used years ago to make pretty graphs wolfram: we locked your account and now you have to pay to upgrade and get access to your files lol me: have you heard of our lord and savior, gdpr? wolfram: … fine, here are your files