talks
conference talks, posters, and tutorials
Date | Venue | Title | Links |
---|---|---|---|
2024-09-11 | Vilnius, Lithuania |
On the robustness of global feature effect explanations | [slides] [paper] [poster] |
2024-07-27 | Vienna, Austria |
Efficient and accurate explanation estimation with distribution compression | [poster] [paper] |
2024-02-12 | Banff, Canada |
Interpretable machine learning for time-to-event prediction in medicine and healthcare | [slides] [video] |
2023-08-31 | Macao, SAR |
Adversarial attacks and defenses in explainable artificial intelligence: A survey | [slides] [paper] |
2023-06-13 | Portoroz, Slovenia |
Hospital length of stay prediction based on multi-modal data towards trustworthy human-AI collaboration in radiomics | [slides] [paper] |
2022-11-05 | Warsaw, Poland |
Interactive sequential analysis of a model improves the performance of human decision-making | [slides] [paper] [video] |
2022-09-21 | Grenoble, France |
Fooling partial dependence via data poisoning | [slides] [paper] [poster] |
2022-08-08 | Washington DC, USA |
dalex: Responsible machine learning with interactive explainability and fairness in Python | [award] [slides] [abstract] [paper] |
2022-02-25 | virtual |
Manipulating SHAP via adversarial data perturbations | [poster] [paper] [demo] |
2021-11-06 | virtual |
Manipulating explainability and fairness in machine learning | [slides] |
2021-07-07 | virtual |
Introduction to responsible machine learning | [materials] [video] |
2021-07-05 | virtual |
Open the machine learning black-box with modelStudio & Arena | [slides] [video] [demo] |
2021-02-06 | virtual |
Responsible prediction making of COVID-19 mortality | [poster] [paper] [demo] |