EPSRC Centre for Doctoral Training in Data Science. Training PhDs in machine learning, databases, stats opt, & analysis of unstructured data at Edinburgh Uni
Joined November 2013
- Tweets 1,091
- Following 267
- Followers 1,102
- Likes 227
64 Photos and videos
31 Jan 2024
Congratulations Tom! The hard work pays off!
31 Jan 2024
My PhD thesis "Modelling Cross-lingual Transfer For Semantic Parsing" is finally submitted! 🎉🎉🎉 #NLProc
1
117
CDT in Data Science retweeted
16 Dec 2023
Poster sessions are happening today! 11:40-1:20 and 5:00-5:30 today in room 208-210.
Come chat transfer learning for Gaussian processes and Bayesian optimisation 🌸
12 Dec 2023
Excited to be in 🎊New Orleans🎊 this week for #NeurIPS2023! Ping me to chat Bayesian optimisation, transfer learning or ML and climate. Or if you know any good runs nearby!
And if you're interested in the above topics you should stop by our poster on Saturday!
7
16
1,373
CDT in Data Science retweeted
8 Dec 2023
Do you love cross-lingual transfer?
Are you interested in putting latent variables everywhere you can?
Desperately searching for applied optimal transport research?
Come to my poster 16:00 in East Foyer! #EMNLP2023
virtual2023.emnlp.org/paper_…
w/ @tomhosking Mirella Lapata
8
65
4,900
CDT in Data Science retweeted
29 Nov 2023
🚨New TACL paper 🚨
Can we use explicit latent variable alignment for cross-lingual transfer? Minotaur uses optimal transport for explicit alignment across languages.
w/ @tomhosking, Mirella Lapata.
To be presented @emnlpmeeting @mrl2023 in-person 🇸🇬
doi.org/10.1162/tacl_a_00611
1
13
55
6,197
CDT in Data Science retweeted
15 Sep 2023
Excited for the poster session this afternoon at @automl_conf! I'll be talking about hyperparameter optimisation for increasing data set sizes and learning between tasks.
Work with Huibin Shen, @FrancoisAubet, David Salinas and @kleiaaro #AutoML23
1 Jul 2023
Finding yourself repeatedly training your ML model because you’ve collected more data? Not sure what to do with the hyperparameters? We investigated for you!
Check out the paper arxiv.org/abs/2306.16916 with the wonderful Huibin Shen, @FrancoisAubet, David Salinas and @kleiaaro
6
21
1,531
CDT in Data Science retweeted
24 Aug 2023
I'm really happy to share the news that Meta-Calibration has been accepted to TMLR! Meta-Calibration uses meta-learning as a new way to optimise for uncertainty calibration of neural networks. I've had a very positive experience with TMLR and certainly recommend submitting there!
24 Aug 2023
Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error
Ondrej Bohdal, Yongxin Yang, Timothy Hospedales.
Action editor: Yingzhen Li.
openreview.net/forum?id=R2hU…
#calibration #prediction #optimise
1
28
923
CDT in Data Science retweeted
22 Aug 2023
Life update: I have passed my PhD defense (@alexandrabirch1 and @licwu were excellent examiners), and moved to New York City!
Many thanks to everyone who made the PhD experience so fun, especially my CDT cohort, collaborators, and supervisor @driainmurray
2
1
43
1,420
CDT in Data Science retweeted
7 Aug 2023
I'm very excited to be in Seoul to give a talk and present a poster about our CVPR'23 Meta Omnium paper at the Hyundai Vision Conference! Feel free to take a look at the poster and also a few photos from this great city! Meta Omnium website: edi-meta-learning.github.io/…
3
23
997
CDT in Data Science retweeted
30 Jul 2023
Interested in what could be the long-term implications of deploying too many AI systems that are not fair? You can learn more in our paper - we've updated it on arXiv with the version that will appear soon in the proceedings of the Stanford Existential Risk Conference!
29 Jul 2023
📢✨ New journal publication alert! ✨📢 @OBohdal, @tmh31 , Phil @OxfordTVG , and I @FazlBarez have dissected a crucial issue: lack of #AIFairness. Our analysis reveals how unfair AI can fuel social stress and unrest over time. 🧵 Here are the main insights: [1/4]
2
8
717
29 Jul 2023
We've also got papers at ICML workshops 🌺🌺🌺
- Will Toner: Label Noise: Correcting a Correction Loss arxiv.org/abs/2307.13100
- @OBohdal: Impact of Noise on Calibration and Generalisation of Neural Networks arxiv.org/abs/2306.17630
1/2
1
1
223
29 Jul 2023
- @sillinuss: Why Do Self-Supervised Models Transfer? On Data Augmentation and Feature Properties icml.cc/virtual/2023/26959
- @sighellan: Bayesian Optimisation Against Climate Change: Applications and Benchmarks arxiv.org/abs/2306.04343
2/2
1
67
28 Jul 2023
Cool work including CDT member Kate!
28 Jul 2023
6. Differentiable Tree Operations Promote Compositional Generalization
Really interesting program induction work! Need to look into it more to digest the details but I always like stuff that tries to respect tree structure
3
214
CDT in Data Science retweeted
24 Jul 2023
Curious about how noise influences uncertainty calibration and generalisation of neural networks? We'll present our new work on this topic at the #ICML2023 SCIS workshop this Saturday! Collaboration with @MartinFerianc, @tmh31, @mrd_rodrigues
24 Jul 2023
Hello from ICML'23! We will be presenting our joint work with @OBohdal, @tmh31, @mrd_rodrigues: Impact of Noise on Calibration and Generalisation of Neural Networks at the Spurious Correlations, Invariance, and Stability Workshop: arxiv.org/abs/2306.17630
2
29
1,551
13 Jul 2023
The CDT has two papers at #ACL2023 this week thanks to @tomsherborne:
- Extrinsic Evaluation of Machine Translation Metrics: An outstanding paper! 🎉🎉🎉
- Meta-Learning a Cross-lingual Manifold for Semantic Parsing
1
7
1,041
11 Jul 2023
🎉🎉🎉
115
10 Jul 2023
Congratulations to CDT student Tom! 🎉🎉🎉
10 Jul 2023
We won outstanding paper at @aclmeeting! Major thanks to my co-authors @nikita_moghe @alexandrabirch1 and Mark Steedman #ACL2023NLP #NLProc
1
182
CDT in Data Science retweeted
5 Jul 2023
I'll be at #ACL2023 next week with 2 papers:
⭐️Extrinsic Evaluation of Machine Translation Metrics (Main conf - Monday Session 2: MT Oral)
⭐️Meta-Learning a Cross-lingual Manifold for Semantic Parsing (TACL - Wednesday Session 7: Semantics)
Reach out if you want to say hello!
1
3
32
3,064
CDT in Data Science retweeted
1 Jul 2023
Finding yourself repeatedly training your ML model because you’ve collected more data? Not sure what to do with the hyperparameters? We investigated for you!
Check out the paper arxiv.org/abs/2306.16916 with the wonderful Huibin Shen, @FrancoisAubet, David Salinas and @kleiaaro
1
6
23
3,246