大葉大學圖書館 |

Variational Bayesian learning theory[electronic resource] /

紀錄類型:	書目-電子資源 : Monograph/item
杜威分類號:	519.233
書名/作者:	Variational Bayesian learning theory/ Shinichi Nakajima, Kazuho Watanabe, Masashi Sugiyama.
作者:	Nakajima, Shin'ichi.
其他作者:	Watanabe, Kazuho.
出版者:	Cambridge : : Cambridge University Press,, 2019.
面頁冊數:	xv, 543 p. : : ill., digital ;; 24 cm.
附註:	Title from publisher's bibliographic system (viewed on 28 Jun 2019).
標題:	Bayesian field theory.
標題:	Probabilities.
ISBN:	9781139879354
ISBN:	9781107076150
ISBN:	9781107430761
摘要、提要註:	Variational Bayesian learning is one of the most popular methods in machine learning. Designed for researchers and graduate students in machine learning, this book summarizes recent developments in the non-asymptotic and asymptotic theory of variational Bayesian learning and suggests how this theory can be applied in practice. The authors begin by developing a basic framework with a focus on conjugacy, which enables the reader to derive tractable algorithms. Next, it summarizes non-asymptotic theory, which, although limited in application to bilinear models, precisely describes the behavior of the variational Bayesian solution and reveals its sparsity inducing mechanism. Finally, the text summarizes asymptotic theory, which reveals phase transition phenomena depending on the prior setting, thus providing suggestions on how to set hyperparameters for particular purposes. Detailed derivations allow readers to follow along without prior knowledge of the mathematical techniques specific to Bayesian learning.
電子資源:	https://doi.org/10.1017/9781139879354

Variational Bayesian learning theory[electronic resource] /
Nakajima, Shin'ichi.

Variational Bayesian learning theory[electronic resource] /Shinichi Nakajima, Kazuho Watanabe, Masashi Sugiyama. - Cambridge :Cambridge University Press,2019. - xv, 543 p. :ill., digital ;24 cm.

Title from publisher's bibliographic system (viewed on 28 Jun 2019).

Variational Bayesian learning is one of the most popular methods in machine learning. Designed for researchers and graduate students in machine learning, this book summarizes recent developments in the non-asymptotic and asymptotic theory of variational Bayesian learning and suggests how this theory can be applied in practice. The authors begin by developing a basic framework with a focus on conjugacy, which enables the reader to derive tractable algorithms. Next, it summarizes non-asymptotic theory, which, although limited in application to bilinear models, precisely describes the behavior of the variational Bayesian solution and reveals its sparsity inducing mechanism. Finally, the text summarizes asymptotic theory, which reveals phase transition phenomena depending on the prior setting, thus providing suggestions on how to set hyperparameters for particular purposes. Detailed derivations allow readers to follow along without prior knowledge of the mathematical techniques specific to Bayesian learning.

ISBN: 9781139879354Subjects--Topical Terms:

558560
Bayesian field theory.

LC Class. No.: QC174.85.B38 / N35 2019

Dewey Class. No.: 519.233

Variational Bayesian learning theory[electronic resource] /
LDR:01894nmm a2200253 a 4500 001 539336
003 UkCbUP
005 20190701083234.0
006 m d
007 cr nn 008maaau
008 231121s2019 enk o 1 0 eng d
020 $a 9781139879354 $q (electronic bk.)
020 $a 9781107076150 $q (hardback)
020 $a 9781107430761 $q (paperback)
035 $a CR9781139879354
040 $a UkCbUP $b eng $c UkCbUP $d GP
050 0 0 $a QC174.85.B38 $b N35 2019
082 0 0 $a 519.233 $2 23
090 $a QC174.85.B38 $b N163 2019
100 1 $a Nakajima, Shin'ichi. $3 767890
245 1 0 $a Variational Bayesian learning theory $h [electronic resource] / $c Shinichi Nakajima, Kazuho Watanabe, Masashi Sugiyama.
260 $a Cambridge : $b Cambridge University Press, $c 2019.
300 $a xv, 543 p. : $b ill., digital ; $c 24 cm.
500 $a Title from publisher's bibliographic system (viewed on 28 Jun 2019).
520 $a Variational Bayesian learning is one of the most popular methods in machine learning. Designed for researchers and graduate students in machine learning, this book summarizes recent developments in the non-asymptotic and asymptotic theory of variational Bayesian learning and suggests how this theory can be applied in practice. The authors begin by developing a basic framework with a focus on conjugacy, which enables the reader to derive tractable algorithms. Next, it summarizes non-asymptotic theory, which, although limited in application to bilinear models, precisely describes the behavior of the variational Bayesian solution and reveals its sparsity inducing mechanism. Finally, the text summarizes asymptotic theory, which reveals phase transition phenomena depending on the prior setting, thus providing suggestions on how to set hyperparameters for particular purposes. Detailed derivations allow readers to follow along without prior knowledge of the mathematical techniques specific to Bayesian learning.
650 0 $a Bayesian field theory. $3 558560
650 0 $a Probabilities. $3 171876
700 1 $a Watanabe, Kazuho. $3 767891
700 1 $a Sugiyama, Masashi. $3 767892
856 4 0 $u https://doi.org/10.1017/9781139879354