國立高雄大學圖資館 |

Language: English

Back

Probabilistic numericscomputation as machine learning /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Probabilistic numericsPhilipp Hennig, Michael A. Osborne, Hans P. Kersting.
Reminder of title:	computation as machine learning /
Author:	Hennig, Philipp.
other author:	Osborne, Michael A.
Published:	Cambridge :Cambridge University Press,2022.
Description:	xii, 398 p. :ill., digital ;25 cm.
Notes:	Title from publisher's bibliographic system (viewed on 10 Jun 2022).
Subject:	Machine learningMathematics.
Online resource:	https://doi.org/10.1017/9781316681411
ISBN:	9781316681411$q(electronic bk.)

Probabilistic numericscomputation as machine learning /
Hennig, Philipp.

Probabilistic numericscomputation as machine learning /[electronic resource] :Philipp Hennig, Michael A. Osborne, Hans P. Kersting. - Cambridge :Cambridge University Press,2022. - xii, 398 p. :ill., digital ;25 cm.

Title from publisher's bibliographic system (viewed on 10 Jun 2022).

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.

ISBN: 9781316681411$q(electronic bk.)Subjects--Topical Terms:

857106
Machine learning
--Mathematics.

LC Class. No.: Q325.5 / .H46 2022

Dewey Class. No.: 006.31

Probabilistic numericscomputation as machine learning /
LDR:01793nmm a2200241 a 4500 001 626747
003 UkCbUP
005 20220620173323.0
006 m d
007 cr nn 008maaau
008 230118s2022 enk o 1 0 eng d
020 $a 9781316681411$q(electronic bk.)
020 $a 9781107163447$q(hardback)
035 $a CR9781316681411
040 $a UkCbUP $b eng $c UkCbUP $d GP
050 4 $a Q325.5 $b .H46 2022
082 0 4 $a 006.31 $2 23
090 $a Q325.5 $b .H516 2022
100 1 $a Hennig, Philipp. $3 930408
245 1 0 $a Probabilistic numerics $h [electronic resource] : $b computation as machine learning / $c Philipp Hennig, Michael A. Osborne, Hans P. Kersting.
260 $a Cambridge : $b Cambridge University Press, $c 2022.
300 $a xii, 398 p. : $b ill., digital ; $c 25 cm.
500 $a Title from publisher's bibliographic system (viewed on 10 Jun 2022).
520 $a 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.
650 0 $a Machine learning $x Mathematics. $3 857106
650 0 $a Computer algorithms. $3 184478
700 1 $a Osborne, Michael A. $3 930409
700 1 $a Kersting, Hans P. $3 930410
856 4 0 $u https://doi.org/10.1017/9781316681411