Machine Learning tools for neuroscience @MackeLab
Tübingen, Deutschland
Joined February 2019
- Tweets54
- Following402
- Followers468
- Likes813
I am super happy to share that our project on training biophysical models with Jaxley is now published in Nature Methods:
nature.com/articles/s41592-0…
Huge thank you to all colleagues and collaborators on this project: @KadhimKyra, @matthijs_pals, @__jnsbck__, @tszwai_wong, @gloecklermanuel, @lappalainenjk, @CorSchroeder, Philipp Berens, Pedro Gonçalves & @jakhmack.
The SBI package has a public discord server now! 🌍 Join if you are a user or (aspiring) contributor, or if you are interested in simulations or Bayesian inference with neural networks!
We are launching an SBI Discord Server! 🎉
We want to use this server to further build a community around SBI, i.e., for sharing insights, questions and events around SBI in general and the sbi package in particular.
You are all invited to join! 🤗 github.com/sbi-dev/sbi/discu…
The sbi toolbox has seen lots of major updates over the past years, many of them driven by new contributors. I am extremely happy to see this happening and we have now written an updated paper to reflect the current state of contributors and features of the toolbox. Check it out!
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
Michael Deistler retweeted
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
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
Oh boy! I am really glad that this is out, and I hope that people find it useful. I have to admit that I am proud of this 🥹
How can we train biophysical neuron models on data or tasks? We built Jaxley, a differentiable, GPU-based biophysics simulator, which makes this possible even when models have thousands of parameters! Led by @deismic_, collab with @CellTypist @ppjgoncalves biorxiv.org/content/10.1101/…
This is the last big project of my PhD, and I am grateful to @jakhmack & @ppjgoncalves for having been fantastic supervisors over the past five years. I also want to thank @CellTypist for having been an amazing collaborator.
Finally, a huge thank you to all co-authors for having made Jaxley much better and for having made this project a lot more fun to work on! @KadhimKyra, @matthijs_pals, @__jnsbck__, @tszwai_wong, @gloecklermanuel, @lappalainenjk, @CorSchroeder
Absolutely amazing work by Janne and team over many years. Big respect. Check it out!
Biggest joy and honour leading this project at the intersection of visual neuroscience and ML to a successful finish! Paper: nature.com/articles/s41586-0…
Michael Deistler retweeted
My #AI4Neuro magnum opus:
Discovery of spiking network model parameters constrained by neural recordings, using simulation-based inference & generative “AI”.
(aka the answer to “how the f did you end up in Tübingen?”)
Here's what we have in store:
biorxiv.org/content/10.1101/…
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! 🚀
Super happy to see this happening! 🚀
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
Join us at oral 6F (4:45pm) or poster 1309 today (1:30pm) to learn how @gloecklermanuel used transformers and diffusion models to build an `All-in-one` SBI method!
@gloecklermanuel and @deismic_ are at ICML to present our work on `All-in-one simulation-based inference`. Join us at ORAL 6F tomorrow (Thursday) 4:45pm, or come by poster 1309, tomorrow 1:30pm!
Michael Deistler retweeted
We are happy to present Simformer, an all-in-one amortized Bayesian inference method. Simformer is flexible and efficient and opens up new possibilities for simulation-based inference. Accepted as oral at ICML 2024.
By @gloecklermanuel @deismic_ @wh1lo @frankdonaldwood @jakhmack
Michael Deistler retweeted
Neural networks are highly sensitive to tiny adversarial perturbations. Can we trust them to reliably perform Bayesian inference?
We investigated the brittleness of inference networks & possible solutions. By @gloecklermanuel @deismic_ @jakhmack, accepted at ICML. 🧵1/5
Michael Deistler retweeted
We are hiring postdocs!
If you're interested in working at the intersection of machine learning and neuroscience, join us in Tübingen @uni_tue to build biologically realistic and task-performing deep neural networks.
Check out the full job ad here: mackelab.org/jobs/
Michael Deistler retweeted
Herzlichen Glückwunsch! Die Biologin Rita Triebskorn erhält den Tübinger Preis für #Wissenschaftskommunikation - Der Nachwuchspreis geht an die KI-Forscherin @SchulzAuguste: uni-tuebingen.de/universitae… #Wisskomm #Biologie #KI
ALT Links im Bild ein Porträtfoto von Rita Triebskorn, rechts im Bild ein Porträtfoto von Auguste Schulz vor einem Mikrofon
Michael Deistler retweeted
📢🧠Got your hands on one of the amazing connectomics data and want to use computational modeling to explore the underlying connectivity principles? Check out the recent preprint by @janfiete @HarthPhilipp @_rdgao @chhege M.Oberlaender @jakhmack et al. doi.org/10.1101/2023.01.31.5… 1/n