國立高雄大學圖資館 |

登入

回首頁

Learning with the minimum description length principle

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Learning with the minimum description length principleby Kenji Yamanishi.
作者:	Yamanishi, Kenji.
出版者:	Singapore :Springer Nature Singapore :2023.
面頁冊數:	xx, 339 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
標題:	Data structures (Computer science)
電子資源:	https://doi.org/10.1007/978-981-99-1790-7
ISBN:	9789819917907$q(electronic bk.)

Learning with the minimum description length principle
Yamanishi, Kenji.

Learning with the minimum description length principle[electronic resource] /by Kenji Yamanishi. - Singapore :Springer Nature Singapore :2023. - xx, 339 p. :ill., digital ;24 cm.

Information and Coding -- Parameter Estimation -- Model Selection -- Latent Variable Model Selection -- Sequential Prediction -- MDL Change Detection -- Continuous Model Selection -- Extension of Stochastic Complexity -- Mathematical Preliminaries.

This book introduces readers to the minimum description length (MDL) principle and its applications in learning. The MDL is a fundamental principle for inductive inference, which is used in many applications including statistical modeling, pattern recognition and machine learning. At its core, the MDL is based on the premise that "the shortest code length leads to the best strategy for learning anything from data." The MDL provides a broad and unifying view of statistical inferences such as estimation, prediction and testing and, of course, machine learning. The content covers the theoretical foundations of the MDL and broad practical areas such as detecting changes and anomalies, problems involving latent variable models, and high dimensional statistical inference, among others. The book offers an easy-to-follow guide to the MDL principle, together with other information criteria, explaining the differences between their standpoints. Written in a systematic, concise and comprehensive style, this book is suitable for researchers and graduate students of machine learning, statistics, information theory and computer science.

ISBN: 9789819917907$q(electronic bk.)

Standard No.: 10.1007/978-981-99-1790-7doiSubjects--Topical Terms:

183917
Data structures (Computer science)

LC Class. No.: QA76.9.D35

Dewey Class. No.: 005.73

Learning with the minimum description length principle
LDR:02414nmm a2200349 a 4500 001 651119
003 DE-He213
005 20230914153802.0
006 m d
007 cr nn 008maaau
008 240327s2023 si s 0 eng d
020 $a 9789819917907$q(electronic bk.)
020 $a 9789819917891$q(paper)
024 7 $a 10.1007/978-981-99-1790-7 $2 doi
035 $a 978-981-99-1790-7
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.9.D35
072 7 $a UMB $2 bicssc
072 7 $a GPF $2 bicssc
072 7 $a COM031000 $2 bisacsh
072 7 $a UMB $2 thema
072 7 $a GPF $2 thema
082 0 4 $a 005.73 $2 23
090 $a QA76.9.D35 $b Y19 2023
100 1 $a Yamanishi, Kenji. $3 961290
245 1 0 $a Learning with the minimum description length principle $h [electronic resource] / $c by Kenji Yamanishi.
260 $a Singapore : $b Springer Nature Singapore : $b Imprint: Springer, $c 2023.
300 $a xx, 339 p. : $b ill., digital ; $c 24 cm.
505 0 $a Information and Coding -- Parameter Estimation -- Model Selection -- Latent Variable Model Selection -- Sequential Prediction -- MDL Change Detection -- Continuous Model Selection -- Extension of Stochastic Complexity -- Mathematical Preliminaries.
520 $a This book introduces readers to the minimum description length (MDL) principle and its applications in learning. The MDL is a fundamental principle for inductive inference, which is used in many applications including statistical modeling, pattern recognition and machine learning. At its core, the MDL is based on the premise that "the shortest code length leads to the best strategy for learning anything from data." The MDL provides a broad and unifying view of statistical inferences such as estimation, prediction and testing and, of course, machine learning. The content covers the theoretical foundations of the MDL and broad practical areas such as detecting changes and anomalies, problems involving latent variable models, and high dimensional statistical inference, among others. The book offers an easy-to-follow guide to the MDL principle, together with other information criteria, explaining the differences between their standpoints. Written in a systematic, concise and comprehensive style, this book is suitable for researchers and graduate students of machine learning, statistics, information theory and computer science.
650 0 $a Data structures (Computer science) $3 183917
650 0 $a Machine learning. $3 188639
650 1 4 $a Data Structures and Information Theory. $3 825714
650 2 4 $a Machine Learning. $3 833608
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-981-99-1790-7
950 $a Computer Science (SpringerNature-11645)