Ed Wagstaff

301 posts

Ed Wagstaff

Ed Wagstaff

@EdWagstaff

Katılım Şubat 2019
547 Takip Edilen457 Takipçiler
Sabitlenmiş Tweet
Ed Wagstaff
Ed Wagstaff@EdWagstaff·
🤖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! edwag.github.io/se3iterative
Ed Wagstaff tweet media
English
1
9
39
0
Ed Wagstaff retweetledi
Petar Veličković
Petar Veličković@PetarV_93·
📢 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!
Fabian Fuchs@FabianFuchsML

I have recently had a range of very insightful conversations with @PetarV_93 about graph neural networks, networks on sets, universality and how ideas have spread in the two communities. This is our write up, feedback welcome as always! :) ➡️fabianfuchsml.github.io/universalgraphs ☕️

English
1
11
56
0
Ed Wagstaff retweetledi
Samuel Stanton
Samuel Stanton@samuel_stanton_·
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! arxiv.org/abs/2210.12496 1/7
Samuel Stanton tweet media
English
4
43
204
0
Ed Wagstaff
Ed Wagstaff@EdWagstaff·
@pfau Could you say any more about which already-known facts about Transformers make this unsurprising?
English
1
1
0
0
David Pfau
David Pfau@pfau·
I genuinely don't understand why people seem so excited by the GATO paper. They took a bunch of independently trained agents, and then amortized all of their policies into a single network? That doesn't seem in any way surprising given what we know about Transformers.
English
43
31
415
0
Ed Wagstaff retweetledi
Freddie Kalaitzis
Freddie Kalaitzis@alkalait·
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
Freddie Kalaitzis tweet media
English
10
10
95
0
Ed Wagstaff
Ed Wagstaff@EdWagstaff·
@razibkhan Tuition fees were capped at £1,000/year in 2000, tripled in 2006, tripled again in 2010.
English
2
0
0
0
Ed Wagstaff retweetledi
Rohin Shah
Rohin Shah@rohinmshah·
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.
English
6
46
458
0
Ed Wagstaff retweetledi
Fabian Fuchs
Fabian Fuchs@FabianFuchsML·
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! :) ➡️fabianfuchsml.github.io/equilibriumagg… ☕️
Fabian Fuchs tweet media
English
6
81
476
0
Ed Wagstaff retweetledi
antonio vergari ⚔️
antonio vergari ⚔️@tetraduzione·
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!
Edinburgh Robotics@EDINrobotics

We have 14 funded places available on our PhD in Robotics and Autonomous Systems programme starting September 2022. More details and how to apply edinburgh-robotics.org/apply

English
7
60
196
0
Ed Wagstaff retweetledi
Shuyu Lin
Shuyu Lin@ShuyuLin_n·
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 😎😎
RoundtableChatroom@RoundtableChat1

🥳 We are proud to present our second event of #RoundtableChatroom at #NeurIPS2021 @NeurIPSConf sponsored by @ivythread ! Save the date: 8-10PM GMT FRI 10 DEC, 2021 (ZOOM) Sign-up: roundtable-chatroom.com Each discussion topic will be guided by a knowledgeable Mentor below ⬇️

English
0
2
6
0
Ed Wagstaff
Ed Wagstaff@EdWagstaff·
@JDHamkins Great post! My immediate thought for the triangle case was angle trisection - it's easy to triple ∠ABC but you can't go back.
English
1
0
3
0
Joel David Hamkins
Joel David Hamkins@JDHamkins·
My analysis of relative constructibility. From segment AB, triangle ABC, if we construct DEF, can we go back? From DEF can we reconstrut original ABC? With segments, yes, we can go back, but with triangles, not necessarily. A hierarchy of constructibility. jdh.hamkins.org/the-hierarchy-…
English
4
6
31
0
Ed Wagstaff retweetledi
John Schwenkler
John Schwenkler@johnschwenkler·
A truly extraordinary footnote.
John Schwenkler tweet media
English
34
476
3.9K
0
Ed Wagstaff retweetledi
Plugin Play
Plugin Play@PluginPlay__·
Playing around with @sportsracer48's new notebook. Taking advantage of the optical flow features and water drops. Wild! #VQGAN #vqganclip
English
1
4
40
0
Arthur Turrell
Arthur Turrell@arthurturrell·
I know I keep going on about this but how awesome is the combination of docker and Visual Studio Code (@code) remote? An isolated environment as easy to use and as accessible as your own laptop 🤩🤯 . Game-changer for reproducibility? Certainly helps. #datascience #R #Python
Arthur Turrell tweet media
English
3
1
10
0
Ed Wagstaff retweetledi
Andy Silvester
Andy Silvester@silvesterldn·
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*
Andy Silvester tweet mediaAndy Silvester tweet mediaAndy Silvester tweet media
English
80
602
2.4K
0