國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Model selection and error estimation...

Oneto, Luca.

Model selection and error estimation in a nutshell

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Model selection and error estimation in a nutshellby Luca Oneto.
作者:	Oneto, Luca.
出版者:	Cham :Springer International Publishing :2020.
面頁冊數:	xiii, 132 p. :ill., digital ;24 cm.
Contained By:	Springer eBooks
標題:	Machine learning.
電子資源:	https://doi.org/10.1007/978-3-030-24359-3
ISBN:	9783030243593$q(electronic bk.)

Model selection and error estimation in a nutshell
Oneto, Luca.

Model selection and error estimation in a nutshell[electronic resource] /by Luca Oneto. - Cham :Springer International Publishing :2020. - xiii, 132 p. :ill., digital ;24 cm. - Modeling and optimization in science and technologies,v.152196-7326 ;. - Modeling and optimization in science and technologies ;v.2..

Introduction -- The "Five W" of MS & EE -- Preliminaries -- Resampling Methods -- Complexity-Based Methods -- Compression Bound -- Algorithmic Stability Theory -- PAC-Bayes Theory -- Diﬀerential Privacy Theory -- Conclusions & Further Readings.

How can we select the best performing data-driven model? How can we rigorously estimate its generalization error? Statistical learning theory answers these questions by deriving non-asymptotic bounds on the generalization error of a model or, in other words, by upper bounding the true error of the learned model based just on quantities computed on the available data. However, for a long time, Statistical learning theory has been considered only an abstract theoretical framework, useful for inspiring new learning approaches, but with limited applicability to practical problems. The purpose of this book is to give an intelligible overview of the problems of model selection and error estimation, by focusing on the ideas behind the different statistical learning theory approaches and simplifying most of the technical aspects with the purpose of making them more accessible and usable in practice. The book starts by presenting the seminal works of the 80's and includes the most recent results. It discusses open problems and outlines future directions for research.

ISBN: 9783030243593$q(electronic bk.)

Standard No.: 10.1007/978-3-030-24359-3doiSubjects--Topical Terms:

188639
Machine learning.

LC Class. No.: Q325.5

Dewey Class. No.: 006.31

Model selection and error estimation in a nutshell
LDR:02371nmm a2200337 a 4500 001 577321
003 DE-He213
005 20200218171150.0
006 m d
007 cr nn 008maaau
008 201130s2020 sz s 0 eng d
020 $a 9783030243593$q(electronic bk.)
020 $a 9783030243586$q(paper)
024 7 $a 10.1007/978-3-030-24359-3 $2 doi
035 $a 978-3-030-24359-3
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.5
072 7 $a UYQ $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQ $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.5 $b .O58 2020
100 1 $a Oneto, Luca. $3 859894
245 1 0 $a Model selection and error estimation in a nutshell $h [electronic resource] / $c by Luca Oneto.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a xiii, 132 p. : $b ill., digital ; $c 24 cm.
490 1 $a Modeling and optimization in science and technologies, $x 2196-7326 ; $v v.15
505 0 $a Introduction -- The "Five W" of MS & EE -- Preliminaries -- Resampling Methods -- Complexity-Based Methods -- Compression Bound -- Algorithmic Stability Theory -- PAC-Bayes Theory -- Diﬀerential Privacy Theory -- Conclusions & Further Readings.
520 $a How can we select the best performing data-driven model? How can we rigorously estimate its generalization error? Statistical learning theory answers these questions by deriving non-asymptotic bounds on the generalization error of a model or, in other words, by upper bounding the true error of the learned model based just on quantities computed on the available data. However, for a long time, Statistical learning theory has been considered only an abstract theoretical framework, useful for inspiring new learning approaches, but with limited applicability to practical problems. The purpose of this book is to give an intelligible overview of the problems of model selection and error estimation, by focusing on the ideas behind the different statistical learning theory approaches and simplifying most of the technical aspects with the purpose of making them more accessible and usable in practice. The book starts by presenting the seminal works of the 80's and includes the most recent results. It discusses open problems and outlines future directions for research.
650 0 $a Machine learning. $3 188639
650 0 $a Computational learning theory. $3 186191
650 0 $a Algorithms. $3 184661
650 1 4 $a Computational Intelligence. $3 338479
650 2 4 $a Statistical Theory and Methods. $3 274054
650 2 4 $a Data Mining and Knowledge Discovery. $3 275288
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer eBooks
830 0 $a Modeling and optimization in science and technologies ; $v v.2. $3 674885
856 4 0 $u https://doi.org/10.1007/978-3-030-24359-3
950 $a Intelligent Technologies and Robotics (Springer-42732)