Welcome to the ENBIS Spring Meeting
Linz, Austria, March 31- April 1, 2027
Statistics and Explainable AI
In an era of increasing algorithmic complexity and growing demands for transparency, accountability, and trustworthiness in AI-driven decision-making, the intersection of statistics and explainable AI (XAI) is becoming critically important. This Spring Meeting aims to serve as a cross-disciplinary platform for researchers, practitioners, and industry experts to exchange cutting-edge developments in statistical methods that enable interpretable and explainable AI systems. At its core, the meeting focuses on how statistical thinking, uncertainty quantification, and rigorous experimental design can enhance the transparency and reliability of AI models, both in theory and in practice. We welcome contributions that advance traditional statistical interpretability methods as well as those that push boundaries using novel approaches to make black-box AI systems more transparent and accountable.
Beyond technical depth, the conference will encourage discussions on strategic challenges including the deployment of XAI in safety-critical systems, regulatory compliance (such as the EU AI Act), and the role of human-in-the-loop approaches in maintaining trust and interpretability. The goal of this Spring Meeting is to facilitate a dynamic exchange of ideas that promotes scientific advancement and its effective translation into practical solutions, fostering meaningful collaboration between statisticians, AI researchers, industry, and society.
Topics of interest include, but are not limited to:
- Interpretable machine learning and statistical models
- Local and global model explanation techniques (LIME, SHAP, etc.)
- Causal inference and counterfactual explanations
- Bayesian methods for interpretable AI models
- Uncertainty quantification and sensitivity analysis in XAI
- Design of experiments for AI model validation and explainability
- Statistical reliability and robustness of explanation methods
- Trustworthy AI and fairness of predictive models
- Explainable AI in medicine and healthcare
- Evaluation and validation of XAI systems
- XAI for time series forecasting and process monitoring
- Ethical, legal, and social implications of XAI
- Trust and transparency in AI-driven decision-making
Organizing committee
Local organization comittee headed by Helmut Waldl
Scientific program committee
Scientific comittee headed by Werner G. Müller