Complexity Reduction, Explainability, and Interpretability (KEI)
-
- Young Academy
- Research Projects
- Complexity Reduction
- Complexity Reduction, Explainability, and Interpretability (KEI)
In Search of Explainable and Interpretable Machine Learning with Philosophy and Physics
Machine learning (ML) algorithms are increasingly permeating our everyday lives and public life. They make predictions, but why they decide one way rather than another often remains difficult to understand; in a sense, they are “opaque.” In our project, we aim to understand how this opacity arises and how it might be retroactively resolved. To this end, we intend to interpret the nature of the (implicit) abstractions that ML generates on its own, drawing on insights from physics and other theories of complexity. Our working hypothesis is that the complexity of ML and the difficulty of understanding certain components of the learning process together give rise to the problem of opacity. In this sense, a solution requires not simply “more understanding” or “less complexity,” but a meaningful reduction in complexity. By this we mean adequate abstractions and non-trivial simplifications that ensure a well-founded approach to understanding . In our project, we will develop tools to analyze the complexity of ML algorithms in new ways and identify meaningful reductions from the perspectives of many-body physics and philosophy .
WIN Fellows
Peer-Reviewed Publications
Bordt, S.; Raidl, E.; von Luxburg, U. (2025): Position: Rethinking Explainable Machine Learning as Applied Statistics, Proceedings of the 42nd International Conference on Machine Learning, PMLR 267: 81130–81142.
Peer-reviewed publications
Klopotek, M. (2026a): Fluctuations in Dynamical Environments: Redefining Computation Emerging, Book chapter for Yearbook for Philosophy of Complex Systems (2nd Ed.) [Eds.: Fraisopi, F. and Saratxaga, Arantzazu].
Raidl, E. (2026): Logics and semantics for “because”, Journal of Logic, Language, and Information, (2nd revision).
Non-peer-reviewed publications
Wetzel, S., … , Klopotek, M. et al. (2025). Interpretable Machine Learning in Physics: A Review, arXiv:2503.23616.
Stein, J. and Raidl, E. (2026): How Complexity Contributes to Learning Opacity in Machine Learning, pp. 1–32, arXiv:2606.24953
Weinmann, M. and Klopotek, M. (2026a): Interpreting Learning Dynamics of Autoencoders: Transient Scaling and Emerging Concepts of the Ising Model, pp. 1–59, arXiv preprint arxiv:2607.10285.
Conferences Organized
Research Frontiers Workshop on Scientific Machine Learning: Navigating the Bermuda Triangle of Knowledge Infusion, Explainability, and Scientific Discovery (A. Guthke, M. Klopotek, E. Raidl, A. Totounferoush) (October 7–10, 2025, Stuttgart). Partially funded by the HAdW/KEI project.
Organoid Intelligence Workshop (A. Wernick, M. Klopotek & D. Kronenberg-Versteeg), Stem Cells in Neuroscience Conference (Feb. 26, 2026, Tübingen).
Presentations (including speeches and posters)
Bordt, S.*; Raidl, E.; von Luxburg, U. (2025): Position: Rethinking Explainable Machine Learning as Applied Statistics (42nd International Conference on Machine Learning, ICML 2025, Vancouver, July 13–19, 2025).
Egenlauf, P.*, Březinová, I., Andergassen, S., and Klopotek, M. (2026b): Neural ODEs for Reduced-Order Quantum Many-Body Dynamics: Assessing Memory Effects (32nd Meeting of the Condensed Matter Division, European Physical Society (CMD) September 20–25, 2026, Graz Center of Physics, Austria).
Egenlauf, P*., Březinová, I., Andergassen, S., and Klopotek, M. (2026b) [poster]: Neural ODEs for Reduced-Order Quantum Many-Body Dynamics: Assessing Memory Effects (Roccella Conference on Inference and AI - ROCKIN' AI, August 31–September 5, 2026, Roccella Jonica, Italy)
Egenlauf, P*., Kröninger, H., Kung, A., and Klopotek, M. (2026b): From Phase Space Fluctuations to Predictive Power: Entropy Production as a Metric for Swarm Reservoir Computing (Spring Meetings of the German Physical Society (DPG): Condensed Matter Section, March 8–14, 2026, March 9, 2026, Dresden).
Gaimann, M. U. and Klopotek, M.* (2026c): “Performing Inference with Physical Response: Reservoir Computing with Active Matter Substrates” (Spring Meetings of the German Physical Society (DPG): Condensed Matter Section, March 8–14, 2026, March 9, 2026, Dresden).
Gaimann, M. U.* and Klopotek, M. (2026d): Reservoir Computing with Active Matter Systems (APS Global Physics Summit, American Physical Society, March 18, 2026, Denver, CO, USA).
Klopotek, M. (2024): A reflection on computational modeling… (SAS24 Conference on Modeling for Policy, HLRS Stuttgart, November 2024)
Klopotek, M. (2025a): Statistical Physics and Machine Learning (presented to scholarship recipients of the Hans-Böckler-Stiftung, March 18, 2025, Stuttgart.)
Klopotek, M. (2025b): From ML interpretability to robustly optimal information processing with active-matter reservoir computers (colloquium at the Vienna University of Technology / invited by I. Brezinova and S. Andergassen, June 35, 2025, Vienna.
Klopotek, M. (2025c) [speech]: The cloud of unknowing: A journey toward AI with physics (commencement/keynote at the Central Doctoral Graduation Ceremony of the University of Tübingen, July 19, 2025, Tübingen).
Klopotek, M. (2025d): Physical roots of computation and learning in malleable uncertainties; Do we need a physical definition of inference? (SAS25 Conference - Uncertainty, HLRS Stuttgart, July 2025)
Klopotek, M. (2025e): Complexity (Research Frontiers Workshop on Scientific Machine Learning: October 6–10, 2025, Stuttgart)
Klopotek, M. (2026b): Reservoir Computing with Biological-like Matter: Basic Perspectives for Future OI [Organoid Intelligence] (Organoid Intelligence Workshop, Stem Cells in Neuroscience Conference, Feb. 26, 2026, Tübingen).
Klopotek, M. (2026c): Basic physics insights from statistical mechanics toward future computing (Future Computing Workshop, HLRS, March 26, 2026, Stuttgart).
Klopotek, M. (2026d): Basic physics insights for embodied intelligence from models of computing in matter (Embodied Intelligence Conference, March 20, 2026, global). Proceedings online [https://www.youtube.com@EmbodiedIntelligenceConference].
Klopotek, M. (2026e): Reservoir Computing with Active Matter: A Statistical-Physical Viewpoint (International Reservoir Computing Conference, March 25–27, 2026, March 25, 2026, Berlin). Proceedings recorded.
Klopotek, M. (2026f): Physical reservoir computing with active matter: Fundamental insights into learning and inference as non-equilibrium statistical mechanics (Academy Day of the Johanna Quandt Young Academy), May 8, 2026, Frankfurt).
Klopotek, M. (2026g) [speech]: Report of the Young Academy (Annual Celebration of the Heidelberg Academy of Sciences and Humanities, June 20, 2026, Heidelberg).
Klopotek, M.* & Raidl, E.* (2026): Understanding Machine Learning—A Physical Perspective (lecture series Insights. For you, July 22, 2026, Heidelberg).
Raidl, E. (2025): Explainability (Research Frontiers Workshop on Scientific Machine Learning: October 6–10, 2025, Stuttgart).
Raidl, E. (2025): Logics for “Because” (“Because” Workshop, November 28, 2025, Mannheim).
Raidl, E. (2026): Explainability and Complexity (Values in Machine Learning, October 16–17, 2026, Konstanz).
Stein, J. (2025): Statistical Learning Theory Meets Formal Learning Theory—Ockham’s Razor and VC Dimension. (German Society for Philosophy of Science Conference, Erlangen, March 24–26, 2025).
Stein, J. (2026): Counteracting Complexity-Driven Opacity in Machine Learning. (University of Groningen TF-PCCP Meeting, Groningen, April 2026).
Stein, J. (2026): Does Mechanistic Interpretability Research Provide Mechanistic Explanations? (SOPhiA 2026 – Salzburg Conference for Young Analytic Philosophy, Salzburg, September 2–4, 2026).
Stein, J.* & Raidl, E. (2025a): On the Complexity of Neural Networks. (Tübingen and Friends Workshop for Philosophy of Machine Learning 2025, Tübingen, April 2025).
Stein, J.* & Raidl, E. (2025b): Complexity and the Opacity of Neural Network Training. (SAS25 Conference on Uncertainty, HLRS Stuttgart, July 28–30, 2025).
Weinmann, M.* and Klopotek, M. (2024): Contextual Alignment for Robust Learning in Dynamical Systems (Spring Meetings of the German Physical Society (DPG): Condensed Matter Section, March 2025, Berlin).
Weinmann, M.* and Klopotek, M. (2026a): Autoencoder Learning Dynamics on MCMC Ising Dataset (Spring Meetings of the German Physical Society (DPG): Condensed Matter Section, March 8–14, 2026, March 9, 2026, Dresden).
Weinmann, M.* and Klopotek, M. (2026b) [poster]: Learning Dynamics of Autoencoders on Ising Model Data (Roccella Conference on Inference and AI - ROCKIN' AI, August 31–September 5, 2026, Roccella Jonica, Italy).
Weinmann, M.* and Klopotek, M. (2026c): Learning Dynamics of Autoencoders on Ising Model Data (32nd Meeting of the Condensed Matter Division, European Physical Society (CMD), September 20–25, 2026, Graz Center of Physics, Austria).
Weinmann, M.* and Klopotek, M. (2026d) [poster]: Learning Dynamics of Autoencoders on Ising Model Data (2026 Bootcamp of the IMPRS-IS, September 23–25, 2026, Sonthofen).
(* indicates the presenter of a contribution with multiple authors listed)
Events or Publications in Science Communication/Knowledge Transfer
Raidl, E. (2026): Interview with André Boße for the magazine “Perspektiven” published by the Baden-Württemberg Foundation. [André Boße: “Should I Tell You How You’re Doing?” On AI and Communication. In: Perspektiven—The Magazine of the Baden-Württemberg Foundation. Issue 01/2026.]
Klopotek, M. (2026d): Prometheus: From Physical Emergence to the Diversification of Artificial Intelligence and Computing, Athene: Magazine of the HAdW (June 2026 issue).
Other Project-Related Publications by the Applicants
Egenlauf, P., …, Klopotek, M. (2026a) Capturing reduced-order quantum many-body dynamics out of equilibrium via neural ordinary differential equations, Machine Learning: Science and Technology 7(2), 025062.
Egenlauf, P., …, Klopotek, M. (2026b) Entropy production of active matter systems as an indicator of computing performance, to appear on arXiv.
Gaimann, M. U. and Klopotek, M. (2026a): Reservoir computing with active matter, Part I: Robustly optimal intrinsic dynamics. Under review (final round), arXiv:2505.05420 preprint (01/2026, v4).
Gaimann, M. U. and Klopotek, M. (2026b): Reservoir computing with active matter, Part II: Optimal information injection and propagation mechanisms. Under Review, arXiv:2509.01799 (3/2026, v2).
Gaimann, M. U., Romero Castillo, A. and Klopotek, M. (2026): Static-Shape Input Encodings as Baselines for Active Matter Reservoir Computing. Manuscript, to be published on arXiv.
Klopotek, M. (2026a): Relations of adaptivity, robustness, and interpretability in beta-VAEs… (working title).
Klopotek, M. (2026h): Nonequilibrium physics of machine inference in active matter reservoir computers (working title) [Invited article].
PD Dr. Eric Raidl
Cluster of Excellence "Machine Learning: New Perspectives for Science"
AI Research Building
Maria-von-Linden-Str. 6
72076 Tübingen
Dr. Miriam Klopotek
University of Stuttgart
Stuttgart Center for Simulation Science
SimTech Cluster of Excellence
Universitätsstraße 32
70569 Stuttgart