126947 20241125101142.0 doi 10.1007/s11831-023-09954-5 sideral 134455 ART-2023-134455 eng Cueto, Elias Universidad de Zaragoza (orcid)0000-0003-1017-4381 Thermodynamics of Learning Physical Phenomena 2023 Access copy available to the general public Unrestricted Thermodynamics could be seen as an expression of physics at a high epistemic level. As such, its potential as an inductive bias to help machine learning procedures attain accurate and credible predictions has been recently realized in many fields. We review how thermodynamics provides helpful insights in the learning process. At the same time, we study the influence of aspects such as the scale at which a given phenomenon is to be described, the choice of relevant variables for this description or the different techniques available for the learning process. info:eu-repo/grantAgreement/ES/DGA-FSE/T24-20R info:eu-repo/grantAgreement/ES/MICINN-AEI/PID2020-113463RB-C31/AEI/10.13039/501100011033 info:eu-repo/grantAgreement/ES/UZ/UZ2019-0060 info:eu-repo/semantics/openAccess by http://creativecommons.org/licenses/by/3.0/es/ 9.7 2023 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS 6 / 170 = 0.035 2023 Q1 T1 MATHEMATICS, INTERDISCIPLINARY APPLICATIONS 2 / 135 = 0.015 2023 Q1 T1 ENGINEERING, MULTIDISCIPLINARY 3 / 181 = 0.017 2023 Q1 T1 1.801 2023 Computer Science Applications 2023 Q1 Applied Mathematics 2023 Q1 19.8 2023 info:eu-repo/semantics/review info:eu-repo/semantics/publishedVersion Chinesta, Francisco 5004 605 Universidad de Zaragoza Dpto. Ingeniería Mecánica Área Mec.Med.Cont. y Teor.Est. 30, 8 (2023), 4653–4666 Arch. comput. methods eng. ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING 1134-3060 1344705 http://zaguan.unizar.es/record/126947/files/texto_completo.pdf Versión publicada 2504864 http://zaguan.unizar.es/record/126947/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:126947 articulos driver 2024-11-22-12:02:54 ARTICLE