Jan Boelts

@giswqs This is awesome @giswqs ! How does integrate with custom models, e.g. could I let it use my fine-tuned SAM variant?

The GeoAI Plugin is now officially available in the official QGIS Plugin Repository! 🎉 With just a few clicks, you can integrate the power of AI-driven spatial analysis right into your QGIS workflow. Important: For a smooth installation, make sure you install QGIS via conda-forge, so it’s compatible with PyTorch and other GeoAI dependencies. 🔗 Plugin Page: plugins.qgis.org/plugins/geoai 📖 Installation Guide: #2-install-the-qgis-plugin" target="_blank" rel="nofollow noopener">opengeoai.org/qgis_plugin/#2… 📺 Full video tutorial: youtu.be/FRKS_g8Begw 👍 Like the plugin? Show your support by giving it a thumbs up on the official plugin page! #QGIS #GeoAI #OpenSource #Python

From hackathon to release: sbi v0.25 is here! 🎉 What happens when dozens of SBI researchers and practitioners collaborate for a week? New inference methods, new documentation, new embedding networks, a bridge to pyro and a bridge between flow matching and score-based methods 🤯

For everyone working with trial-based i.i.d. data and varying experimental conditions - we have you covered now! You can train NLE once and then run MCMC with multiple subjects, trials and conditions, etc. Example: sbi-dev.github.io/sbi/dev/tutori… Reach out on GitHub for questions 🙋‍♂️

So happy to be part of this project and see it growing! Many thanks to all contributors and users for making it possible 🚀

We have an exciting talk coming up tomorrow at 4pm CEST in the TransferLab seminar! Join us for an introduction to Reduced Order Modeling and how surrogate models can accelerate large-scale engineering workflows. More details below and here: transferlab.ai/seminar/2024/i…

Looking for some physics-enhanced machine learning insights this Thursday afternoon? 🧠 Join us for the upcoming TransferLab talk on "generalized quadratic embeddings for nonlinear dynamics".

Absolutely! Huge kudos to @FrancoisRozet for Zuko—it’s incredibly smooth and efficient, also for flow matching! 🚀 Can’t wait to try out Azula next! 🔥

Make sure to check out the fresh look of our docs website: sbi-dev.github.io/sbi/🎨 Big thanks to @tomamoral for the incredible help and kudos to github.com/jimporter/mike, making docs version switching so seamless.

So excited to see the new SBI release out just in time for today’s talk at #EuroSciPy2024! 🎉 A big shoutout to all the new contributors who made this possible. Thank you all! 🙏 Names are here: github.com/sbi-dev/sbi/re…

Excited to present the SBI toolkit at #EuroSciPy2024 next week! 🎉 I’ll introduce SBI and show how @sbi_devs gives user-friendly access to the latest methods for Bayesian parameter inference on scientific simulators. See you there! #OpenSource #Python

Really happy to see this come to life! 🚀

🚆 Heading to #icml2024? Need a good read for the journey? Check out the paper summaries I wrote at transferlab.ai! 📚 📝 "All-in-One SBI", outstanding work by Gloeckler et al. (oral) @mackelab 📝 "Position: Leverage LLMs for BBO" by the amazing @RobertTLange et al.

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

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/

@RobertTLange @mackelab @jakhmack Thank you, Robert!

@janfiete @mackelab @jakhmack Big congrats, Jan! All the best for whatever is next 🚀

Finally done 👨‍🎓🥳 Many thanks to the amazing @mackelab and @jakhmack for supporting and guiding me on this journey!

Neural oscillations are abundant! But what is their role? Oscillations could serve as a clock signal for phase-coding information. In: biorxiv.org/content/10.110…, we studied the dynamical systems underlying this kind of coding. With @matthijs_pals, @jakhmack and Omri Barak [1/5]

I am so happy and honoured that my efforts to bring ML and AI education into schools are recognised by @uni_tue. Being part of the network @KImachtSchule and building this wonderful subgroup here in Tübingen has been fantastic, and I hope that more people will join in.