切換：
- 簡略
- 詳細(MARC)
- ISBD
-
Variational Bayesian learning theory
紀錄類型 ： 書目-語言資料,印刷品: 單行本
正題名/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).
電子資源 ： https://doi.org/10.1017/9781139879354
ISBN ： 9781139879354
ISBN ： 9781107076150
ISBN ： 9781107430761
LEADER 01894nam a2200253 a 4500
001 224773
003 UkCbUP
005 20190701083234.0
006 m d
007 cr nn 008maaau
008 140211s2019 enk o 1 0 eng d
020 $a9781139879354$q(electronic bk.)
020 $a9781107076150$q(hardback)
020 $a9781107430761$q(paperback)
035 $aCR9781139879354
040 $aUkCbUP$beng$cUkCbUP$dGP
050 00$aQC174.85.B38$bN35 2019
082 00$a519.233$223
090 $aQC174.85.B38$bN163 2019
100 1 $aNakajima, Shin'ichi.$3292998
245 10$aVariational Bayesian learning theory$h[electronic resource] /$cShinichi Nakajima, Kazuho Watanabe, Masashi Sugiyama.
260 $aCambridge :$bCambridge University Press,$c2019.
300 $axv, 543 p. :$bill., digital ;$c24 cm.
500 $aTitle from publisher's bibliographic system (viewed on 28 Jun 2019).
520 $aVariational Bayesian learning is one of the most popular methods in machine learning. Designed for researchers and graduate students in machine learning, this book summarizes recent developments in the non-asymptotic and asymptotic theory of variational Bayesian learning and suggests how this theory can be applied in practice. The authors begin by developing a basic framework with a focus on conjugacy, which enables the reader to derive tractable algorithms. Next, it summarizes non-asymptotic theory, which, although limited in application to bilinear models, precisely describes the behavior of the variational Bayesian solution and reveals its sparsity inducing mechanism. Finally, the text summarizes asymptotic theory, which reveals phase transition phenomena depending on the prior setting, thus providing suggestions on how to set hyperparameters for particular purposes. Detailed derivations allow readers to follow along without prior knowledge of the mathematical techniques specific to Bayesian learning.
650 0$aBayesian field theory.$3293001
650 0$aProbabilities.$3268267
700 1 $aWatanabe, Kazuho.$3292999
700 1 $aSugiyama, Masashi.$3293000
856 40$uhttps://doi.org/10.1017/9781139879354
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:
293001
Bayesian field theory.
LC Class. No.: QC174.85.B38 / N35 2019
Dewey Class. No.: 519.233
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:
293001
Bayesian field theory.
LC Class. No.: QC174.85.B38 / N35 2019
Dewey Class. No.: 519.233
- 館藏(0)
- 心得(0)
- 標籤
發表心得