@guymoss13

Machine Learning + Glaciology. PhD student @mackelab, @uni_tue.

Joined December 2021
  • Tweets33
  • Following78
  • Followers64
6Media
🙏 Please help us improve the SBI toolbox! 🙏 In preparation for the SBI Hackathon, we’re running a user study to learn what we can improve and how we can grow. 👉 Please share your thoughts here: forms.gle/foHK7myV2oaK1NU57 Your input will make a big difference—thank you! 🙌

SBI User Study

Dear SBI User, We're committed to making the SBI toolbox the best possible tool for your simulation-based inference needs. To achieve this, we're seeking your feedback on the SBI toolbox. We are...

docs.google.com
4
4
632
Thrilled to announce we have three #NeurIPS2024 papers! Interested in simulating realistic neural data with diffusion models or recurrent neural networks, or in source distribution sorcery? Have a look 👇 1/4
6
6
1
28
3,172
We introduce a new maximum-entropy, sample-based approach to solve the source distribution estimation problem. Poster #4006 (East; Fri 13 Dec 11:00 PT). By Julius Vetter, @guymoss13, ➡️openreview.net/forum?id=0cgD… 4/4
2
5
412
The sbi package is growing into a community project 🌎 To reflect this and the algorithms, neural nets, and diagnostics that have been added since its initial release, we have written a new software paper. Reach out if you want to get involved: arxiv.org/abs/2411.17337

sbi reloaded: a toolkit for simulation-based inference workflows

Scientists and engineers use simulators to model empirically observed phenomena. However, tuning the parameters of a simulator to ensure its outputs match observed data presents a significant...

arxiv.org
1
11
2
32
3,939
A propos: Inspired to do a PhD or Postdoc in #ML4Science/#AI4Science? We have multiple openings to work ML and AI tools for scientific discovery, in neuroscience and beyond! Full details: mackelab.org/media/Ad_Mackel… Students: Apply by Nov 15, directly to IMPRS-IS or @ELLISforEurope
Intelligent Systems@MPI_IS24 Sep 2024
Researching #AI #MachineLearning #Robotics #HCI? Join our elite doctoral program - a partnership with MPI-IS, @uni_stuttgart & @uni_tue! Applications accepted until Nov 15, 2024 at imprs.is.mpg.de/application
1
9
4
37
44,734
I hacked together a semantic search engine for ICLR 2025 paper submissions! 🔍📄 Uses OpenAI embeddings and BM25 reranking. Anecdotally, it feels much more useful than the OpenReview search button! Try it out now: iclr-search.jkapoor.me (Fun fact, I did not write a single line of non-python code. @cursor_ai is insanely powerful🧠)
3
24
2,554
We’re at Bernstein Conference next week with lots of new work to share: 10 posters, 1 workshop talk, and don’t miss @jakhmack’s invited talk on Wednesday! If you’re excited about machine learning for (neuro)science, come chat with us—we’re hiring PhD students & postdocs!
1
7
1
19
3,774
We’re stoked to share: “A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Science”. Now out in TMLR: openreview.net/forum?id=isEF… This was an incredibly special project for us, as it involved the **entire** lab getting together!
3
52
3
214
23,347
Puh, we have been preparing the new release of the sbi toolbox for quite a while now, and I am really glad to see it out now! Have a look, there are a lot of cool new features! 🚀
sbi developers@sbi_devs29 Aug 2024
We just released a new version of `sbi`, and this one has _a ton_ of new features! Many of these features are thanks to more than 30 (mostly new) contributors. We are very excited about the growing community and the new release! 🧵 1/8
4
1
31
1,633
We just released a new version of `sbi`, and this one has _a ton_ of new features! Many of these features are thanks to more than 30 (mostly new) contributors. We are very excited about the growing community and the new release! 🧵 1/8
1
20
9
49
15,961
We’re excited to share that the SBI package is now officially @NumFOCUS affiliated and growing into a community project. A lot of upcoming release originated from a hackathon earlier this year, and there are more events planned soon. Stay tuned for details! #opensource #hackathon
7
2
24
1,986
Guy Moss retweeted
Max Eggl@maxeggl15 Apr 2024
Just came from organising the the bio-inspired deep learning workshop with @BernaezLaura and lead by @ppjgoncalves. It was an absolutely fantastic experience and with great projects that I hope will lead to further collaboration.
4
6
1,438
What does this dog have to do with a sh!tty data project? In the scope of the Data Literacy course, two of our students Michelle Schlicher and Karsten Binz analyzed as a real-world problem whether there is a connection between the meals of their dog Buddy and his diarrhea. (1/8)
2
4
3
14
4,703
Come work with us! We have an open PostDoc position in "Simulation-based model discovery" at Uni Tübingen in cooperation with Boehringer Ingelheim AI: uni-tuebingen.de/en/universi…
6
1
6
1,836
Stoked to share my first #NeurIPS2022 paper. "Efficient Identification of informative features in SBI" arxiv.org/abs/2210.11915 w. @deismic_, @yvesbernaerts, @jakhmack, @CellTypist @ml4science We use NLE to efficiently identify how features constrain posteriors in SBI. (1/8)
1
4
28
New research article: Predicting the steady-state isochronal stratigraphy of ice shelves using observations and modeling doi.org/10.5194/tc-16-4763-2…
4
4
Ice rises and rumples in 3D and with hysteresis when sea level changes. Great work by @_clarahenry ! tc.copernicus.org/articles/1… @VjeranV @Schannwell @ElmerIce1

Hysteretic evolution of ice rises and ice rumples in response to variations in sea level

Abstract. Ice rises and ice rumples are locally grounded features found in coastal Antarctica and are surrounded by otherwise freely floating ice shelves. An ice rise has an independent flow regime,...

tc.copernicus.org
5
11
Reminder: There is more space in Tübingen's geophysics boat for a 2 x 3 years Postdoc. Come join us! tinyurl.com/5absxcva (First deadline is by the end of this week.)
5
2
22
📢We released a new version of SBI with many improvements and one highlight🎉: We enabled access to ArviZ (@arviz_devs) to benefit from their amazing MCMC diagnostics and inference visualizations 🤩 (thanks to @sethaxen)! see github.com/mackelab/sbi/rele… for details 1/2

Release v0.19.0 · sbi-dev/sbi

Major changes and bug fixes new option to sample posterior using importance sampling (#692) new option to use arviz for posterior plotting and MCMC diagnostics (#546, #607, thanks to @sethaxen) fi...

github.com
1
5
30
Simulation-based inference (SBI) has accelerated model-building across many disciplines. It’s also useful for studying cognition: We present Mixed Neural Likelihood Estimation, an SBI method tailored to models of decision-making! By @janfiete @janmatthis @_rdgao @jakhmack 1/5
1
29
5
98
Load more