{"id":111,"date":"2023-02-28T15:39:26","date_gmt":"2023-02-28T14:39:26","guid":{"rendered":"https:\/\/udnneng.wordpress.com\/?page_id=111"},"modified":"2026-02-18T15:34:34","modified_gmt":"2026-02-18T15:34:34","slug":"publications","status":"publish","type":"page","link":"https:\/\/udnn.tu-dortmund.de\/index.php\/publications\/","title":{"rendered":"Publications &amp; Presentations"},"content":{"rendered":"\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-28f84493 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:100%\">\n<figure class=\"wp-block-image alignfull size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1568\" height=\"459\" src=\"https:\/\/udnn.tu-dortmund.de\/wp-content\/uploads\/2023\/03\/bckgrnd.jpg\" alt=\"\" class=\"wp-image-163\" srcset=\"https:\/\/udnn.tu-dortmund.de\/wp-content\/uploads\/2023\/03\/bckgrnd.jpg 1568w, https:\/\/udnn.tu-dortmund.de\/wp-content\/uploads\/2023\/03\/bckgrnd-300x88.jpg 300w, https:\/\/udnn.tu-dortmund.de\/wp-content\/uploads\/2023\/03\/bckgrnd-1024x300.jpg 1024w, https:\/\/udnn.tu-dortmund.de\/wp-content\/uploads\/2023\/03\/bckgrnd-768x225.jpg 768w, https:\/\/udnn.tu-dortmund.de\/wp-content\/uploads\/2023\/03\/bckgrnd-1536x450.jpg 1536w\" sizes=\"auto, (max-width: 1568px) 100vw, 1568px\" \/><\/figure>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-group is-layout-constrained wp-block-group-is-layout-constrained\">\n<h2 class=\"wp-block-heading\">Project-Related Publications<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Boge, F.J., Schuster, A. and Stoll, F. (forthcoming). <a href=\"https:\/\/www.sciencedirect.com\/special-issue\/328936\/scientific-understanding-and-machine-learning-in-science-from-traditional-themes-to-recent-developments-and-new-vistas\">Special Issue: Scientific understanding and Machine Learning in science: From traditional themes to recent developments and new vistas<\/a>, <em>Studies in History and Philosophy of Science<\/em><\/li>\n\n\n\n<li>Schuster, A. (2026). <a href=\"https:\/\/doi.org\/10.1007\/s11229-025-05426-4\">Understanding Protein Folding with Machine Learning? The Case of AlphaFold2<\/a>, <em>Synthese<\/em>, doi: 10.1007\/s11229-025-05426-4<\/li>\n\n\n\n<li>Boge, F. J. (forthcoming). <a href=\"http:\/\/dx.doi.org\/10.17877\/DE290R-26418\">The Influence of Artificial Intelligence on Scientific Knoweldge and the Role of the Philosophy of Technology: A Philosophy of Science Perspecive<\/a> [in German], in Friedrich, A., Gehring, P., Nordmann, A., Hubig, C. &amp; Kaminski, A. (eds), <em>Jahrbuch Technikphilosophie<\/em>, Nomos<\/li>\n\n\n\n<li>Boge, F. J. (forthcoming). <a href=\"https:\/\/philsci-archive.pitt.edu\/id\/eprint\/26251\">Understanding (and) Machine Learning\u2019s Black Box Explanation Problems<\/a>, in Curtis-Trudel, A., Barack, D., and Rowbottom, D. P. (eds), <em>The Role of Artificial Intelligence in Science: Methodological and Epistemological Studies<\/em>, Routledge <\/li>\n\n\n\n<li>Boge, F. J. and de Regt, H. W. (2025). <a href=\"https:\/\/philsci-archive.pitt.edu\/id\/eprint\/26255\">Machine Learning Discoveries and Scientific Understanding in Particle Physics: Problems and Prospects<\/a>, in: Duran, J. M., and Pozzi, G. (Eds.), <em>Philosophy of Science for Machine Learning<\/em>, Synthese Library, Springer<\/li>\n\n\n\n<li>Boge, F. J. &amp; Schuster, A. (2025). <a href=\"https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&amp;arnumber=11229371\">How can we Trust Opaque Systems? Criteria for Robust Explanations in XAI<\/a>, <em>2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy <\/em><\/li>\n\n\n\n<li>Boge, F. J. &amp; Mosig, A. (2025). <a href=\"https:\/\/doi.org\/10.1007\/s11023-025-09724-1\">Put it to the Test: Getting Serious About Explanation in Explainable Artificial Intelligence<\/a>, <em>Minds and Machines<\/em>, 35(26), doi: 10.1007\/s11023-025-09724-1<\/li>\n\n\n\n<li>Boge, F. J. (2025). Models: Measuring or Cognitive Instruments? <em>Journal for General Philosophy of Science<\/em>, doi: 10.1007\/s10838-025-09733-9<\/li>\n\n\n\n<li>Boge, F. J. (2024). <a href=\"https:\/\/doi.org\/10.1017\/psa.2024.23\">Re-Assessing the Experiment \/ Observation-Divide<\/a>, <em>Philosophy of Science<\/em>, do: 10.1017\/psa.2024.23<\/li>\n\n\n\n<li>Mosig, A. and Boge, F. J. (2024). <a href=\"https:\/\/doi.org\/10.1007\/s00424-024-03033-9\">Causality and Scientific Explanation of Artificial Intelligence Systems in Biomedicine<\/a>, <em>European Journal of Physiology, <\/em>doi:10.1007\/s00424-024-03033-9<\/li>\n\n\n\n<li>Boge, F. J. (2024). <a href=\"https:\/\/doi.org\/10.1007\/s11229-023-04440-8\">Functional Concept Proxies and the Actually Smart Hans Problem: What\u2019s Special About Deep Neural Networks in Science<\/a>, <em>Synthese<\/em>, doi: 10.1007\/s11229-023-04440-8<\/li>\n\n\n\n<li>Boge, F. J. (2022). <a href=\"https:\/\/doi.org\/10.1007\/s11023-021-09569-4\">Two Dimensions of Opacity and the Deep Learning Predicament<\/a>, <em>Minds and Machines,<\/em> 32(1), pp. 43-75, doi: 10.1007\/s11023-021-09569-4<\/li>\n\n\n\n<li>Boge, F. J., Hillerbrand R., and Gr\u00fcnke, P. (2022). Introduction: <a href=\"https:\/\/doi.org\/10.1007\/s11023-022-09597-8\">Machine Learning: Prediction Without Explanation?<\/a> <em>Minds and Machines<\/em>, 32(1), pp. 1-11, doi: 10.1007\/s11023-022-09597-8<\/li>\n\n\n\n<li>Boge, F. J., Hillerbrand R., and Gr\u00fcnke, P. (2022). <a href=\"https:\/\/link.springer.com\/journal\/11023\/volumes-and-issues\/32-1\">Machine Learning: Prediction Without Explanation?<\/a>, <em>Minds and Machines<\/em> Special Issue, 32(1)<\/li>\n\n\n\n<li>Boge, F. J. (2021). <a href=\"https:\/\/doi.org\/10.1086\/716542\">Why Trust a Simulation? Models, Parameters, and Robustness in Simulation-Infected Experiments<\/a>,&nbsp;<em> British Journal for the Philosophy of Science, <\/em>doi: 10.1086\/716542<\/li>\n\n\n\n<li>Boge, F. J. and Poznic, M. (2021). Meeting report: <a href=\"https:\/\/dx.doi.org\/10.1007\/s10838-020-09537-z\">Machine Learning and the Future of Scientific Explanation<\/a>, <em>Journal for General Philosophy of Science<\/em> 52(1), 171\u2013176, doi: 10.1007\/s10838-020-09537-z<\/li>\n\n\n\n<li>Boge, F. J. and Gr\u00fcnke, P. (2019). <a href=\"http:\/\/philsci-archive.pitt.edu\/17637\/\">Computer Simulations, Machine Learning and the Laplacean Demon: Opacity in the Case of High Energy Physics<\/a>, forthcoming in Resch, Kaminski, and Gehring (Eds.), <em>The Science and Art of Simulation II, <\/em>Springer<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Presentations<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Boge, F.J.: &#8222;Inside the Chinese Library: Why There Still is no Strong Claim to Strong AI&#8220;, <em> AISolA Conference <\/em>, Nov 2025, Rhodes (Greece) <\/li>\n\n\n\n<li>Stoll, F.: &#8222;Deep Neural Networks as Mediators: Rethinking Deep Learning and Scientific Understanding&#8220;, <em>Oxford Philosophy Graduate Conference<\/em>, Nov 25, University of Oxford<\/li>\n\n\n\n<li> Boge, F.J.: &#8222;Put it to the Test: Getting Serious About Explanation in XAI&#8220;, <em> SciML Conference <\/em>, Oct 25, Stuttgart University <\/li>\n\n\n\n<li>Schuster, A.: \u201cMental, Scientific, and Artificial Representations?\u201d (with Nina Poth), <em>GAP conference<\/em>, Sep 25, HHU D\u00fcsseldorf<\/li>\n\n\n\n<li>Stoll, F.: &#8222;Understanding (with) Deep Neural Networks in Particle Physics&#8220;, <em>GAP Conference<\/em>, Sep 25, Heinrich-Heine Universit\u00e4t D\u00fcsseldorf<\/li>\n\n\n\n<li>Stoll, F.: &#8222;Understanding (with) Deep Neural Networks in Particle Physics&#8220;, <em>EPSA Conference<\/em>, Aug 25, Groningen<\/li>\n\n\n\n<li>Schuster, A. &amp; Boge, F.J.: \u201cHow can we trust opaque systems? Criteria for robust explanations in XAI\u201d, <em>IACAP conference<\/em>, Jul 25, University of Twente<\/li>\n\n\n\n<li>Boge, F.J.: \u201cA Novel Approach to the Pessimistic Induction\u201d, <em>Research Colloquium Theoretical Philosophy<\/em>, Jun 25, HHU D\u00fcsseldorf<\/li>\n\n\n\n<li>Stoll, F.: \u201cEmpirical and Theoretical Links: Rethinking the Role of DNNs in Scientific Understanding\u201d, <em>Epistemology and Theory of ML Workshop<\/em>, May 25, LMU Munich<\/li>\n\n\n\n<li>Stoll, F.: \u201cA Multi-Layered Approach to Scientific Understanding with DNNs\u201c, <em>Mini PhilML Workshop<\/em>, Apr 25, T\u00fcbingen University<\/li>\n\n\n\n<li>Schuster, A.: \u201cSHAPley Values &#8211; Subjective Objectivity in XAI\u201d, <em>Mini PhilML workshop<\/em>, Apr 25, T\u00fcbingen University<\/li>\n\n\n\n<li>Stoll, F.: \u201cStart Making Sense: Understanding Particle Physics with Deep Neural Networks and Explainable AI\u201d, <em>GWP Conference<\/em>, Mar 25, FAU Erlangen\/N\u00fcrnberg<\/li>\n\n\n\n<li>Schuster, A.: \u201cFrom objectual to explanatory understanding with AlphaFold2\u201d, <em>GWP conference<\/em>, Mar 25, FAU Erlangen<\/li>\n\n\n\n<li>Schuster, A. &amp; Boge, F.J.: Symposium: \u201cAdvancing Understanding: XAI at Interfaces between Machine Learning, Life Sciences, and Philosophy\u201d, <em>Lamarr Lab Visits<\/em>, Feb 25, TU Dortmund University (with J\u00fcrgen Bajorath &amp; Andrea Mastopietro)<\/li>\n\n\n\n<li>Schuster, A.: \u201cFrom objectual to explanatory understanding with AlphaFold2\u201d, <em>Lamarr Lab Visits<\/em>, Feb 25<\/li>\n\n\n\n<li>Stoll, F.: \u201cUnderstanding particle physics with DNNs and XAI\u201d, <em>Artificial Intelligence and the Future of Science Conference<\/em>, Nov 24, Lingnan University Hong Kong<\/li>\n\n\n\n<li>Schuster, A.: \u201cFrom Objectual to Explanatory Understanding with Alphafold2\u201d, <em>AI and the Future of Science Conference<\/em>, Nov 24, Lingnan University Hong Kong<\/li>\n\n\n\n<li>Boge, F.J.: \u201cRe-Assessing Machine Cognition in the Age of Deep Learning\u201d, <em>Bayreuth Research Forum<\/em>, Oct 24, Bayreuth University<\/li>\n\n\n\n<li>Schuster, A. &amp; Stoll, F.: \u201cUnderstanding without understanding\u201c, <em>PhilML Conference<\/em>, Sep 24, T\u00fcbingen University<\/li>\n\n\n\n<li>Stoll, F.: \u201cEpistemological Issues of Machine Learning in Science\u201d, <em>Machine Learning Journal Club<\/em>, Aug 24, RWTH Aachen University<\/li>\n\n\n\n<li>Boge, F.J.: \u201cWhat is Special About Deep Learning Opacity?\u201d, <em>Special Lecture Series on Philosophy of Science<\/em>, Aug 24, Seoul National University<\/li>\n\n\n\n<li>Boge, F.J.: \u201cRe-Assessing Machine Cognition in the Age of Deep Learning\u201d, <em>Special Lecture Series on Philosophy of Science<\/em>, Aug 24, Seoul National University (special lecture)<\/li>\n\n\n\n<li>Boge, F.J.: \u201cUnderstanding (and) Machine Learning\u2019s Black Box Explanation Problems\u201d, <em>Mini-Workshop on Philosophy of Science<\/em>, Aug 24, Seoul National University (special lecture)<\/li>\n\n\n\n<li>Schuster, A.: \u201cA new pathway to scientific understanding &#8211; From objectual to explanatory understanding with AlphaFold2\u201d, <em>IACAP conference<\/em>, Jul 24, University of Oregon<\/li>\n\n\n\n<li>Boge, F.J. &amp; Stoll, F.: Symposium: \u201cDeep Neural Networks in Particle Physics: Aids or Obstacles to Understanding?\u201d, <em>BSPS 2024 Annual Conference<\/em>, Jul 24, University of York (with H.W. de Regt, and M. King)<\/li>\n\n\n\n<li>Stoll, F.: \u201cNavigating the Black-Box\u201d, <em>6th SURe Workshop<\/em>, Jun 24, London School of Economics<\/li>\n\n\n\n<li>Schuster, A.: \u201cUnderstanding Deep Learning Geometrically \u2013 Conceptual Spaces in Deep Neural Networks&#8220;, <em>6th SURe Workshop<\/em>, Jun 24, London School of Economics<\/li>\n\n\n\n<li>Schuster, A.: \u201cA new pathway to scientific understanding \u2013 From objectual to explanatory understanding with AlphaFold2\u201d, <em>Philosophy of Science and Epistemology Conference<\/em>, Jun 24, Hong Kong University of Science and Technology<\/li>\n\n\n\n<li>Boge, F.J.: \u201cPut it to the Test: Getting Serious about Explanation in XAI\u201d, <em>Colloquium Digitale<\/em>, Jun 24, RU Bochum University<\/li>\n\n\n\n<li>Schuster, A.: \u201cUnderstanding deep learning geometrically\u201d, <em>Rationality and Cognition Workshop<\/em>, May 24, RU Bochum<\/li>\n\n\n\n<li>Boge, F.J.: \u201cRe-Assessing the Experiment \/ Observation Divide\u201d, <em>Wuppertal Philosophy of Physics Meeting<\/em>, May 24, BU Wuppertal University<\/li>\n\n\n\n<li>Schuster, A. &amp; Stoll, F.: \u201cPathways towards scientific understanding with Deep Neural Networks\u201d, <em>49th Philosophy of Science Conference<\/em>, Apr 24, Inter-University Center Dubrovnik<\/li>\n\n\n\n<li>Boge, F.J.: \u201cPut it to the Test: Getting Serious about Explanation in XAI\u201d, <em>49th Philosophy of Science Conference<\/em>, Apr 24, Inter-University Center Dubrovnik<\/li>\n\n\n\n<li>Boge, F.J.: \u201cPut it to the Test: Getting Serious about Explanation in XAI\u201d, <em>Ethics of AI (Un-)Explainability<\/em>, Mar 24, M\u00fcnster University<\/li>\n\n\n\n<li>Stoll, F.: \u201cNavigating the Black-Box: Understanding Particle Physics with Deep Neural Networks and XAI\u201d, <em>Epistemological Issues of Machine Learning in Science Workshop<\/em>, Feb 24, TU Dortmund University<\/li>\n\n\n\n<li>Schuster, A.: \u201cA new pathway to scientific understanding\u201d, <em>Epistemological Issues of Machine Learning in Science Workshop<\/em>, Feb 24, TU Dortmund University<\/li>\n\n\n\n<li>Schuster, A. &amp; Stoll, F.: \u201cScientific Understanding and Deep Neural Networks\u201d, <em>Explainable Intelligent Systems Colloquium<\/em>, Jan 24, online<\/li>\n\n\n\n<li>Boge, F.J.: \u201cUnderstanding (and) Machine Learning\u2019s Black Box Explanation Problems in Science\u201d, <em>DoDaS Research Colloquium<\/em>, Jan 24, TU Dortmund University<\/li>\n\n\n\n<li>Boge, F.J.: \u201cDeep Learning for Scientific Discovery and the Theory Freedom-Robustness Trade-Off\u201d, <em>History and Philosophy of Physics Seminar<\/em>, Jan 24, Bonn University<\/li>\n\n\n\n<li>Boge, F.J.: \u201cUnderstanding (and) Machine Learning\u2019s Black Box Explanation Problems in Science\u201d, <em>The Philosophy of AI in Science<\/em>, Dec 23, University of Cambridge<\/li>\n\n\n\n<li>Stoll, F.: \u201eAnalogy- and Interaction-based Model Transfer: The Case of Black Hole Thermodynamics\u201d, <em>Model Transfer in Science Workshop<\/em>, Nov 23, LU Hannover<\/li>\n\n\n\n<li>Boge, F.J.: \u201cThree Notions of Observation and the Experiment \/ Observation Divide\u201d, <em>PoS around the World Conference<\/em>, Nov 23<\/li>\n\n\n\n<li>Boge, F.J.: \u201cDeep Learning for Scientific Discovery and the Theory Freedom-Robustness Trade-Off\u201d, <em>Philosophy of Experiment Conference<\/em>, Nov 23, Stockholm University<\/li>\n\n\n\n<li>Boge, F.J.: \u201cRealism Without Interphenomena: Reichenbach\u2019s Cube and Quantum Solipsism\u201d, <em>Reconsidering Solipsism Workshop<\/em>, Oct 23, University of Vienna<\/li>\n\n\n\n<li>Boge, F.J.: \u201cUnderstanding (and) Machine Learning\u2019s Black Box Explanation Problems\u201d, <em>AITE Conference<\/em>, Oct 23, University of T\u00fcbingen<\/li>\n\n\n\n<li>Boge, F.J.: \u201cDeep Learning Robustness for Scientific Discovery: The Case of Anomaly Detection\u201d, <em>PhilML: Philosophy of Science Meets Machine Learning Conference<\/em>, Sep 23, University of T\u00fcbingen (opening lecture)<\/li>\n\n\n\n<li>Boge, F.J.: Symposium: \u201cMachine Learning in Contemporary &amp; Future Science\u201d, <em>BSPS 2023 Annual Conference<\/em>, Jul 23, University of Bristol (with A. Curtis Trudel, W. Pedden and E. Sullivan)<\/li>\n\n\n\n<li>Boge, F.J.: \u201cLocal Holism and a Puzzle About Confirmation\u201d, <em>Colloquium for the History and Philosophy of Science<\/em>, May 23, RU Bochum<\/li>\n\n\n\n<li>Boge, F.J.: \u201cDeep Learning Robustness for Scientific Discovery: The Case of Anomaly Detection\u201d, <em>The VEIL Online Lectures<\/em>, Jun 23, University of L\u00fcbeck<\/li>\n<\/ul>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Project-Related Publications Presentations<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":3,"comment_status":"closed","ping_status":"closed","template":"header-footer-only","meta":{"footnotes":""},"class_list":["post-111","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/udnn.tu-dortmund.de\/index.php\/wp-json\/wp\/v2\/pages\/111","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/udnn.tu-dortmund.de\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/udnn.tu-dortmund.de\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/udnn.tu-dortmund.de\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/udnn.tu-dortmund.de\/index.php\/wp-json\/wp\/v2\/comments?post=111"}],"version-history":[{"count":43,"href":"https:\/\/udnn.tu-dortmund.de\/index.php\/wp-json\/wp\/v2\/pages\/111\/revisions"}],"predecessor-version":[{"id":1083,"href":"https:\/\/udnn.tu-dortmund.de\/index.php\/wp-json\/wp\/v2\/pages\/111\/revisions\/1083"}],"wp:attachment":[{"href":"https:\/\/udnn.tu-dortmund.de\/index.php\/wp-json\/wp\/v2\/media?parent=111"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}