Pack up, it‘s a retreat! 🚌 Over the next 3 days, the DataNinja 🥷 research training group meets up to discuss cutting-edge #MachineLearning research promoting #TrustworthyAI for seamless problem solving. Research powered by mkw.nrw. Learn more here: dataninja.nrw

Great news🥳 Joint work of André Artelt from Faculty of Technology Bielefeld Bielefeld University and Kleanthis Malialis from KIOS Research and Innovation Center of Excellence University of Cyprus on "Unsupervised Unlearning of Concept Drift with Autoencoders" got accepted at IEEE Computational Intelligence Society #SSCI Check out the preprint👇 arxiv.org/abs/2211.12989 #MachineLearning

Official version out now: Our #xAI23 paper "For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior" published Springer Nature's CCIS series! Check it out (fully #OpenAccess, of course 😉): rdcu.be/dppYX ... or dive into the 🧵👇

📢SAIL event coming up: On Nov 23, a hybrid workshop on "Fundamental Limits of #LargeLanguageModels" will take place. The program will contain a series of invited talks by esteemed researchers around the world.🤩👏 ➡️Further information & registration: sites.google.com/view/sail-ws-l…

📢Reminder 👉 Upcoming Event: This week the hybrid workshop "Fundamental Limits of Large Language Models" will take place.🤩 See sites.google.com/view/sail-ws-l… for further information.

📢Open #PhD position in David Johnson's new research group on "Human-Centric #Explainable #AI for Mental Health Assessment". 🔽🔽🔽

🔥New Explainable AI to be presented NeurIPS Conference #NeurIPS2023: We propose SHAP-IQ as a unified approximation of any-order Shapley Interactions! 📖Paper link: openreview.net/forum?id=IEMLN… ⚡️The highlights are in the🧵(1/5)!

We are at IEEE Computational Intelligence Society #SSCI 😃 This Thursday (December 7th) at 1:30 pm📅, André Artelt is going to present joint work with Kleanthis Malialis from KIOS Research and Innovation Center of Excellence University of Cyprus on "Unsupervised Unlearning of Concept Drift with Autoencoders"👇 github.com/andreArtelt/Un… #MachineLearning

Researchers @FumagalliFabian and @Muschalik_Max from our subproject C03 will be attending NeurIPS Conference 2023 in #NewOrleans from December 10-16 . It’s the 36th onference on Neural Information Processing Systems. They'll be presenting a poster. See Fabian's thoughts 👀⬇

📢Call for Papers! "Explainable Online Learning from Uncertain Data Streams" will be a Special Session IEEE EAIS 2024 in Madrid. Co-organized by SAIL member Daniel Leite, we would like to draw your attention to the CFP below.✍️🧑‍💼 ➡️More information here: sites.google.com/view/olud/home

Approx. one month left📅 to submit your work to WSOM+ 2024👇 hosted in beautiful Mittweida @hsmw forschung.hs-mittweida.de/en/webs/welcom…

Please retweet🤓 We are organizing a special session on "Machine Learning in Critical Infrastructure" at IEEE WCCI-2024 in Yokohama, Japan🇯🇵 Deadline📅 15.01.2024 Details: sites.google.com/view/wcci24mlc… #WCCI2024 #IEEE #AI

#TrustworthyAI fans in and around #NRW: 📢Free in-person registration is still open! Expect exciting keynote talks by great experts, panels, posters, and networking opportunities at 🥷DataNinja sAIOnARA 2024 Conference 📅June 25-27 📍Bielefeld Details: dataninja.nrw/?p=2071

June 20 at 4:15pm, we welcome Nicole Ludwig to our lecture series "Robust AI" Bielefeld University.👏 Come along or join us online when she talks about "Assessing Climate Change Impacts: An ML Approach to Multi-Decadal Energy Forecasting".👩‍💻👍 ➡️More info here: sail.nrw/2024/06/lectur…

IJCAIconf, the #XAI tutorial by our own André Artelt and Dr. Ulrike Kuhl, together with Mark Keane, is in session! It started with a history of counterfactuals in psychology and first basics of user studies, followed by computational foundations of computing counterfactuals.

#Tutorial At the T06: All You Ever Need to Know About Counterfactual Explanations: Fundamentals, Methods, & User Studies for XAI, with Ulrike Kuhl Dr. Ulrike Kuhl on the speaker's podium. sites.google.com/view/tut-count… #IJCAI2024

IJCAIconf I‘ve had a great time presenting the basics of how to run effective user studies to explore the usability of XAI! Anyone who’s curious: The materials (slides and code) are available GitHub: github.com/andreArtelt/IJ… ✨Thanks to everyone attending this full day program! ✨

It’s a wrap on the tutorial on #counterfactuals and user studies for #XAI IJCAIconf. Anyone who’s curious: The materials (slides and code) are available GitHub: github.com/andreArtelt/IJ… For more info about the general program, visit sites.google.com/view/tut-count…

🎉Exciting News! Our own André Artelt & his Water-Futures ERC colleagues just won the Best Poster 🏆 at the '#AI for Critical Infrastructure Workshop' IJCAIconf, presenting the EPyT-Flow Toolbox!🧰 📜➡️arxiv.org/abs/2406.02078 🧑‍💻➡️@GitHub: github.com/WaterFutures/E… Congratulations!

Andre Artelt applied DataSHAP to investigate the effect of training data samples on explanation. A paper with lovely theory and a nice case study using this to investigate group fairness. Interesting results.