Thermodynamics of Learning Physical Phenomena

Cueto, Elias (Universidad de Zaragoza) ; Chinesta, Francisco

Resumen: 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.

Idioma: Inglés

DOI: 10.1007/s11831-023-09954-5

Año: 2023

Publicado en: ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING 30, 8 (2023), 4653–4666
ISSN: 1134-3060

Factor impacto JCR: 9.7 (2023)

Categ. JCR: COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS rank: 6 / 170 = 0.035 (2023) - Q1 - T1
Categ. JCR: MATHEMATICS, INTERDISCIPLINARY APPLICATIONS rank: 2 / 135 = 0.015 (2023) - Q1 - T1
Categ. JCR: ENGINEERING, MULTIDISCIPLINARY rank: 3 / 181 = 0.017 (2023) - Q1 - T1

Factor impacto CITESCORE: 19.8 - Computer Science Applications (Q1) - Applied Mathematics (Q1)

Factor impacto SCIMAGO: 1.801 - Computer Science Applications (Q1) - Applied Mathematics (Q1)

Financiación: info:eu-repo/grantAgreement/ES/DGA-FSE/T24-20R
Financiación: info:eu-repo/grantAgreement/ES/MICINN-AEI/PID2020-113463RB-C31/AEI/10.13039/501100011033
Financiación: info:eu-repo/grantAgreement/ES/UZ/UZ2019-0060

Tipo y forma: Revisión (Versión definitiva)

Área (Departamento): Área Mec.Med.Cont. y Teor.Est. (Dpto. Ingeniería Mecánica)