Online-Ressource
Verfasst von:	Hennig, Philipp [VerfasserIn]
	Osborne, Michael A. [VerfasserIn]
	Kersting, Hans [VerfasserIn]
Titel:	Probabilistic numerics
Titelzusatz:	computation as machine learning
Verf.angabe:	Philipp Hennig, Michael A. Osborne, Hans P. Kersting
Verlagsort:	Cambridge
Verlag:	Cambridge University Press
Jahr:	2022
Umfang:	1 Online-Ressource (xii, 398 Seiten)
Fussnoten:	Title from publisher's bibliographic system (viewed on 10 Jun 2022)
ISBN:	978-1-316-68141-1
Abstract:	Probabilistic numerical computation formalises the connection between machine learning and applied mathematics. Numerical algorithms approximate intractable quantities from computable ones. They estimate integrals from evaluations of the integrand, or the path of a dynamical system described by differential equations from evaluations of the vector field. In other words, they infer a latent quantity from data. This book shows that it is thus formally possible to think of computational routines as learning machines, and to use the notion of Bayesian inference to build more flexible, efficient, or customised algorithms for computation. The text caters for Masters' and PhD students, as well as postgraduate researchers in artificial intelligence, computer science, statistics, and applied mathematics. Extensive background material is provided along with a wealth of figures, worked examples, and exercises (with solutions) to develop intuition.
DOI:	doi:10.1017/9781316681411
URL:	Resolving-System: https://doi.org/10.1017/9781316681411
	DOI: https://doi.org/10.1017/9781316681411
Schlagwörter:	(s)Numerische Mathematik    / (s)Unsicherheit    / (s)Unvollkommene Information    / (s)Wahrscheinlichkeit    / (s)Maschinelles Lernen
	(s)Numerische Integration    / (s)Numerische lineare Algebra    / (s)Optimierung    / (s)Gewöhnliche Differentialgleichung    / (s)Numerisches Verfahren
Datenträger:	Online-Ressource
Sprache:	eng
Bibliogr. Hinweis:	Erscheint auch als : Druck-Ausgabe: Hennig, Philipp: Probabilistic numerics. - Cambridge : Cambridge University Press, 2022. - xii, 398 Seiten
RVK-Notation:	SK 920
K10plus-PPN:	1810622158
	Universitätsbibliothek
Lokale URL UB:	Zum Volltext