Deep Learning Discrete Calculus (DLDC): a family of discrete numerical methods by universal approximation for STEM education to frontier research

The article proposes formulating and codifying a set of applied numerical methods, coined as D eep L earning D iscrete C alculus (DLDC), that uses the knowledge from discrete numerical methods to interpret the deep learning algorithms through the lens of applied mathematics. The DLDC methods aim to...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computational mechanics Jg. 72; H. 2; S. 311 - 331
Hauptverfasser:	Saha, Sourav, Park, Chanwook, Knapik, Stefan, Guo, Jiachen, Huang, Owen, Liu, Wing Kam
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Berlin/Heidelberg Springer Berlin Heidelberg 01.08.2023 Springer Springer Nature B.V
Schlagworte:	Algorithms Applications of mathematics Calculus Classical and Continuum Physics Codification Computational Science and Engineering Data mining Deep learning Differential equations Engineering Equipment and supplies Finite difference method Finite element method Integral equations Machine learning Mathematical analysis Methods Numerical analysis Numerical methods Original Paper Teaching Technical education Theoretical and Applied Mechanics Convolution Numerical methods Kernel learning Partial differential equation Discrete calculus
ISSN:	0178-7675, 1432-0924
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!