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.
@IJCAIconf, the #XAI tutorial by our own André Artelt and @DrUlrikeKuhl, together with @keanema, 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.
@IJCAIconf, the #XAI tutorial by our own André Artelt and @DrUlrikeKuhl, together with @keanema, 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.
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/IJCAI…
✨Thanks to everyone attending this full day program! ✨
June 20 at 4:15pm, we welcome Nicole Ludwig to our lecture series "Robust AI" @unibielefeld.👏 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/lecture-ser…
#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
Please retweet🤓
We are organizing a special session on "Machine Learning in Critical Infrastructure" at @IEEEorg WCCI-2024 in Yokohama, Japan🇯🇵 Deadline📅 15.01.2024
Details: sites.google.com/view/wcci24…#WCCI2024#IEEE#AI
📢Call for Papers! "Explainable Online Learning from Uncertain Data Streams" will be a Special Session @eais2024 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/h…
Researchers @FumagalliFabian and @Muschalik_Max from our subproject C03 will be attending @NeurIPSConf 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 👀⬇
Excited to announce that my new research group, Human-Centered & Explainable AI, is starting in the new year at @CITEC_Bielefeld. This means I have a fully funded #PhD position to study the effect of #xai in AI-assisted decision-making. If interested 👉 uni-bielefeld.hr4you.org/job…
ALT Illustration how SHAP-IQ can efficiently compute Shapley Interaction scores and enrich the feature attribution explanation of a sentiment analysis model.
📢Reminder 👉 Upcoming Event: This week the hybrid workshop "Fundamental Limits of Large Language Models" will take place.🤩
See sites.google.com/view/sail-w… for further information.
📢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-w…
📢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-w…
Official version out now: Our #xAI23 paper "For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior" published @SpringerNature's CCIS series! Check it out (fully #OpenAccess, of course 😉): rdcu.be/dppYX
... or dive into the 🧵👇
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