Philosophy of Science for Machine Learning

This open access book offers a comprehensive and systematic debate on the key concepts and areas of application of the philosophy of science for machine learning. The current landscape of the debate about the epistemic and methodological challenges raised by machine learning in scientific fields is fragmented and lacks a common thread that helps to understand the complexity of the issue. Against this background, this book brings together expert researchers in the field, structuring the debate in ways that allow readers to navigate quickly in this evolving field of research and pave the way to new paths of philosophical and technical research. Although the book is written from the perspective of philosophy of science and epistemology, it is of interest to philosophers in a myriad of fields, such as philosophy of mind, philosophy of language, philosophy of neuroscience, and metaphysics of science, STS studies, as well as to researchers working on technical and computational issues such as explainability, trustworthiness, interpretability, transparency.

Part I: Epistemic opacity. - 1 In Which Ways is Machine Learning Opaque? (Claus Beisbart). - 2 How I Stopped Worrying and Learned to Love Opacity (Nico Formanek). - 3 Epistemic opacity and scientific realism and anti-realism (Jack Casey). - Part II: Justification. - 4 Beyond transparency: computational reliabilism as an externalist epistemology for algorithms (Juan M. Durán). - 5 Challenges for Computational Reliabilism: Epistemic Warrants, Endogeneity and Error-Based Opacity in Machine Learning (Ramón Alvarado). - 6 Can XAI Justify? (Carlos Zednik, Philippe Verreault-Julien). - Part III: Scientific Explanation (XAI) . - 7 Axe the X in XAI: A Plea for Understandable AI (Andrés Páez). - 8 Machine Learning models as Mathematics (Stefan Buijsman). - 9 From Explanations to Interpretability and Back (Tim Räz). - Part IV: Scientific Understanding and Interpretability. - 10 Explanation hacking: The Perils of Algorithmic Recourse (Emily Sullivan, Atoosa Kasirzadeh). - 11 Stakes and Understanding the Decisions of Artificial Intelligent Systems (Eva Schmidt). - Part V: Scientific Models and Representation. - 12 Representation Learning Without Representationalism. A Non-Representationalist Account of Deep Learning Models in Scientific Practice (Phillip Hintikka Kieval). - 13 Artificial Neural Nets and the Representation of Human Concepts (Timo Freisleben). - 14 Defining Formal Validity Criteria for Machine Learning Models (Chiara Manganini, Giuseppe Primiero). - Part VI: Scientific practice and scientific values in ML. - 15 Why are Human Epistemic Agents not Displaced in Machine Learning Scientific Inquiries? (Sahra A. Styger, Marianne de Heer Kloots, Oskar van der Wal, and Federica Russo). - 16 Values, Inductive Risk, and Societal-Epistemic Coupledness in Machine Learning Models (Milou Jansen, Koray Karaca). - 17 Machine Learning and the Ethics of Induction (Emanuele Ratti). - Part VII: ML in the Particular Sciences. - 18 Beyond Classification and Prediction: The Promise of Physics-Informed Machine Learning in Astronomy and Cosmology (Helen Meskhidze). - 19 Machine Learning Discoveries and Scientific Understanding in Particle Physics: Problems and Prospects (Florian J. Boge and Henk W. de Regt). - 20 Don t Fear the Bogeyman: On Why There is no Prediction-Understanding Trade-Off for Deep-Learning in Neuroscience (Barnaby Crook, Lena Kästner). - 21 Artificial Intelligence in Climate Science: From Machine Learning to Neural Networks (Greg Lusk). - 22 Machine Learning in Public Health and the Prediction-Intervention Gap (Thomas Grote, Oliver Buchholz).