Scientific Understanding and Deep Neural Networks

Project-Related Publications

Presentations

  • Stoll, F. “Coordinating Machine Learning Models for Measurement” PSA 2026, Nov 2026, UC San Diego
  • Boge, F. J. “The Epistemic Alignment Problem of Machine Learning” PSA 2026, Nov 2026, UC San Diego
  • Schuster, A., Poth, N. “Deflating Artificial Representations”, Workshop on Functions and Representations in AI Systems, Nov 2026, Copenhagen, Denmark.
  • Fracchioni, R. “Scientific Understanding from Machine Learning Failures” International Philosophy Student Symposium, Nov 2026, Maribor University
  • Fracchioni, R. “The Epistemic Significance of Machine Learning Failures in Science” Philosophy of Machine Learning Conference, Oct 2026, LMU Munich
  • Schuster, A. “Philosophy of Science and AI”, Beyond equations: AI, Models, and the Future of Theoretical Biology Sandpit Workshop, Oct 2026, Heidelberg, Germany
  • Schuster, A., Galli, G. “Can AI generate Scientific Representations of Proteins?”, Lecture Series Philosophy of AI in Science and Beyond, Oct 2026, Dortmund, Germany
  • Schuster, A. “Illusions of Objectivity in XAI”, Keynote at Workshop: Philosophy of Explainable AI: New Directions, Jul 2026, Aarhus, Denmark
  • Stoll, F. “Lost in Translation? Testimonial Understanding from Deep Neural Networks” SURe,  May 2026, Polish Academy of Science
  • Fracchioni, R. “Three Dimensions of LLMs’ Understanding and Why We Confuse Them” 6th International Conference on Philosophy of Mind, May 2026, University of Porto
  • Boge, F. J. “Inside the Chinese Library: Why There Still is no Strong Claim to Strong AI”, Philosophy Colloquium, May 2026, HHU Düsseldorf
  • Schuster, A. “The Paradox of Explainability in XAI”, 8th International Conference in Philosophy and Economics, May 2026, Nancy, France.
  • Schuster, A., Galli, G. “Can AI generate Scientific Representations of proteins? A DEKI-analysis of AlphaFold2”, SURe, May 2026, Warsaw, Poland.
  • Boge, F. J. “From Robustness to Trustworthy Explanations in XAI: A Normative Framework”, Lamarr Workshop on Trustworthy AI, Apr 2026, TU Dortmund University
  • Stoll. F. “Lost in Translation? Testimonial Scientific Understanding from Machine Learning” Workshop Scientific Understanding in the Age of Machine Learning, Feb 2026, Radboud University Nijmegen 
  • Boge, F. J. “The Epistemic Alignment Problem of Machine Learning”, Workshop Scientific Understanding in the Age of Machine Learning, Feb 2026, Radboud University Nijmegen
  • Stoll, F. “From Machine to Mind: Transferring Understanding from Machine Learning” Institute for Science in Society Colloquium, Feb 2026, Radboud University Nijmegen
  • Boge, F.J.: „Inside the Chinese Library: Why There Still is no Strong Claim to Strong AI“, AISolA Conference , Nov 2025, Rhodes (Greece)
  • Stoll, F.: „Deep Neural Networks as Mediators: Rethinking Deep Learning and Scientific Understanding“, Oxford Philosophy Graduate Conference, Nov 25, University of Oxford
  • Boge, F.J.: „Put it to the Test: Getting Serious About Explanation in XAI“, SciML Conference , Oct 25, Stuttgart University
  • Schuster, A. “Representations: mental, scientific – and artificial?”, 6th Conference on Philosophy of Artificial Intelligence (PhAI 2025), Oct 2025, Amsterdam, Netherlands.
  • Schuster, A.: “Mental, Scientific, and Artificial Representations?” (with Nina Poth), GAP conference, Sep 25, HHU Düsseldorf
  • Stoll, F.: „Understanding (with) Deep Neural Networks in Particle Physics“, GAP Conference, Sep 25, Heinrich-Heine Universität Düsseldorf
  • Stoll, F.: „Understanding (with) Deep Neural Networks in Particle Physics“, EPSA Conference, Aug 25, Groningen
  • Schuster, A. & Boge, F.J.: “How can we trust opaque systems? Criteria for robust explanations in XAI”, IACAP conference, Jul 25, University of Twente
  • Boge, F.J.: “A Novel Approach to the Pessimistic Induction”, Research Colloquium Theoretical Philosophy, Jun 25, HHU Düsseldorf
  • Stoll, F.: “Empirical and Theoretical Links: Rethinking the Role of DNNs in Scientific Understanding”, Epistemology and Theory of ML Workshop, May 25, LMU Munich
  • Stoll, F.: “A Multi-Layered Approach to Scientific Understanding with DNNs“, Mini PhilML Workshop, Apr 25, Tübingen University
  • Schuster, A.: “SHAPley Values – Subjective Objectivity in XAI”, Mini PhilML workshop, Apr 25, Tübingen University
  • Stoll, F.: “Start Making Sense: Understanding Particle Physics with Deep Neural Networks and Explainable AI”, GWP Conference, Mar 25, FAU Erlangen/Nürnberg
  • Schuster, A.: “From objectual to explanatory understanding with AlphaFold2”, GWP conference, Mar 25, FAU Erlangen
  • Schuster, A. & Boge, F.J.: Symposium: “Advancing Understanding: XAI at Interfaces between Machine Learning, Life Sciences, and Philosophy”, Lamarr Lab Visits, Feb 25, TU Dortmund University (with Jürgen Bajorath & Andrea Mastopietro)
  • Schuster, A.: “From objectual to explanatory understanding with AlphaFold2”, Lamarr Lab Visits, Feb 25
  • Stoll, F.: “Understanding particle physics with DNNs and XAI”, Artificial Intelligence and the Future of Science Conference, Nov 24, Lingnan University Hong Kong
  • Schuster, A.: “From Objectual to Explanatory Understanding with Alphafold2”, AI and the Future of Science Conference, Nov 24, Lingnan University Hong Kong
  • Boge, F.J.: “Re-Assessing Machine Cognition in the Age of Deep Learning”, Bayreuth Research Forum, Oct 24, Bayreuth University
  • Schuster, A. & Stoll, F.: “Understanding without understanding“, PhilML Conference, Sep 24, Tübingen University
  • Stoll, F.: “Epistemological Issues of Machine Learning in Science”, Machine Learning Journal Club, Aug 24, RWTH Aachen University
  • Boge, F.J.: “What is Special About Deep Learning Opacity?”, Special Lecture Series on Philosophy of Science, Aug 24, Seoul National University
  • Boge, F.J.: “Re-Assessing Machine Cognition in the Age of Deep Learning”, Special Lecture Series on Philosophy of Science, Aug 24, Seoul National University (special lecture)
  • Boge, F.J.: “Understanding (and) Machine Learning’s Black Box Explanation Problems”, Mini-Workshop on Philosophy of Science, Aug 24, Seoul National University (special lecture)
  • Schuster, A.: “A new pathway to scientific understanding – From objectual to explanatory understanding with AlphaFold2”, IACAP conference, Jul 24, University of Oregon
  • Boge, F.J. & Stoll, F.: Symposium: “Deep Neural Networks in Particle Physics: Aids or Obstacles to Understanding?”, BSPS 2024 Annual Conference, Jul 24, University of York (with H.W. de Regt, and M. King)
  • Stoll, F.: “Navigating the Black-Box”, 6th SURe Workshop, Jun 24, London School of Economics
  • Schuster, A.: “Understanding Deep Learning Geometrically – Conceptual Spaces in Deep Neural Networks“, 6th SURe Workshop, Jun 24, London School of Economics
  • Schuster, A.: “A new pathway to scientific understanding – From objectual to explanatory understanding with AlphaFold2”, Philosophy of Science and Epistemology Conference, Jun 24, Hong Kong University of Science and Technology
  • Boge, F.J.: “Put it to the Test: Getting Serious about Explanation in XAI”, Colloquium Digitale, Jun 24, RU Bochum University
  • Schuster, A.: “Understanding deep learning geometrically”, Rationality and Cognition Workshop, May 24, RU Bochum
  • Boge, F.J.: “Re-Assessing the Experiment / Observation Divide”, Wuppertal Philosophy of Physics Meeting, May 24, BU Wuppertal University
  • Schuster, A. & Stoll, F.: “Pathways towards scientific understanding with Deep Neural Networks”, 49th Philosophy of Science Conference, Apr 24, Inter-University Center Dubrovnik
  • Boge, F.J.: “Put it to the Test: Getting Serious about Explanation in XAI”, 49th Philosophy of Science Conference, Apr 24, Inter-University Center Dubrovnik
  • Boge, F.J.: “Put it to the Test: Getting Serious about Explanation in XAI”, Ethics of AI (Un-)Explainability, Mar 24, Münster University
  • Stoll, F.: “Navigating the Black-Box: Understanding Particle Physics with Deep Neural Networks and XAI”, Epistemological Issues of Machine Learning in Science Workshop, Feb 24, TU Dortmund University
  • Schuster, A.: “A new pathway to scientific understanding”, Epistemological Issues of Machine Learning in Science Workshop, Feb 24, TU Dortmund University
  • Schuster, A. & Stoll, F.: “Scientific Understanding and Deep Neural Networks”, Explainable Intelligent Systems Colloquium, Jan 24, online
  • Boge, F.J.: “Understanding (and) Machine Learning’s Black Box Explanation Problems in Science”, DoDaS Research Colloquium, Jan 24, TU Dortmund University
  • Boge, F.J.: “Deep Learning for Scientific Discovery and the Theory Freedom-Robustness Trade-Off”, History and Philosophy of Physics Seminar, Jan 24, Bonn University
  • Boge, F.J.: “Understanding (and) Machine Learning’s Black Box Explanation Problems in Science”, The Philosophy of AI in Science, Dec 23, University of Cambridge
  • Stoll, F.: „Analogy- and Interaction-based Model Transfer: The Case of Black Hole Thermodynamics”, Model Transfer in Science Workshop, Nov 23, LU Hannover
  • Boge, F.J.: “Three Notions of Observation and the Experiment / Observation Divide”, PoS around the World Conference, Nov 23
  • Boge, F.J.: “Deep Learning for Scientific Discovery and the Theory Freedom-Robustness Trade-Off”, Philosophy of Experiment Conference, Nov 23, Stockholm University
  • Boge, F.J.: “Realism Without Interphenomena: Reichenbach’s Cube and Quantum Solipsism”, Reconsidering Solipsism Workshop, Oct 23, University of Vienna
  • Boge, F.J.: “Understanding (and) Machine Learning’s Black Box Explanation Problems”, AITE Conference, Oct 23, University of Tübingen
  • Boge, F.J.: “Deep Learning Robustness for Scientific Discovery: The Case of Anomaly Detection”, PhilML: Philosophy of Science Meets Machine Learning Conference, Sep 23, University of Tübingen (opening lecture)
  • Boge, F.J.: Symposium: “Machine Learning in Contemporary & Future Science”, BSPS 2023 Annual Conference, Jul 23, University of Bristol (with A. Curtis Trudel, W. Pedden and E. Sullivan)
  • Boge, F.J.: “Local Holism and a Puzzle About Confirmation”, Colloquium for the History and Philosophy of Science, May 23, RU Bochum
  • Boge, F.J.: “Deep Learning Robustness for Scientific Discovery: The Case of Anomaly Detection”, The VEIL Online Lectures, Jun 23, University of Lübeck