國立高雄大學圖資館 |

Language: English

Back

Automated machine learningmethods, s...

Hutter, Frank.

Automated machine learningmethods, systems, challenges /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Automated machine learningedited by Frank Hutter, Lars Kotthoff, Joaquin Vanschoren.
Reminder of title:	methods, systems, challenges /
other author:	Hutter, Frank.
Published:	Cham :Springer International Publishing :2019.
Description:	xiv, 219 p. :ill., digital ;24 cm.
Contained By:	Springer eBooks
Subject:	Machine learning.
Online resource:	https://doi.org/10.1007/978-3-030-05318-5
ISBN:	9783030053185$q(electronic bk.)

Automated machine learningmethods, systems, challenges /
Automated machine learningmethods, systems, challenges /[electronic resource] :edited by Frank Hutter, Lars Kotthoff, Joaquin Vanschoren. - Cham :Springer International Publishing :2019. - xiv, 219 p. :ill., digital ;24 cm. - The Springer series on challenges in machine learning,2520-131X. - Springer series on challenges in machine learning..

1 Hyperparameter Optimization -- 2 Meta-Learning -- 3 Neural Architecture Search -- 4 Auto-WEKA -- 5 Hyperopt-Sklearn -- 6 Auto-sklearn -- 7 Towards Automatically-Tuned Deep Neural Networks -- 8 TPOT -- 9 The Automatic Statistician -- 10 AutoML Challenges.

Open access.

This open access book presents the first comprehensive overview of general methods in Automated Machine Learning (AutoML), collects descriptions of existing systems based on these methods, and discusses the first series of international challenges of AutoML systems. The recent success of commercial ML applications and the rapid growth of the field has created a high demand for off-the-shelf ML methods that can be used easily and without expert knowledge. However, many of the recent machine learning successes crucially rely on human experts, who manually select appropriate ML architectures (deep learning architectures or more traditional ML workflows) and their hyperparameters. To overcome this problem, the field of AutoML targets a progressive automation of machine learning, based on principles from optimization and machine learning itself. This book serves as a point of entry into this quickly-developing field for researchers and advanced students alike, as well as providing a reference for practitioners aiming to use AutoML in their work.

ISBN: 9783030053185$q(electronic bk.)

Standard No.: 10.1007/978-3-030-05318-5doiSubjects--Topical Terms:

188639
Machine learning.

LC Class. No.: Q325.5

Dewey Class. No.: 006.31

Automated machine learningmethods, systems, challenges /
LDR:02415nmm a2200349 a 4500 001 558673
003 DE-He213
005 20190517163533.0
006 m d
007 cr nn 008maaau
008 191219s2019 gw s 0 eng d
020 $a 9783030053185$q(electronic bk.)
020 $a 9783030053178$q(paper)
024 7 $a 10.1007/978-3-030-05318-5 $2 doi
035 $a 978-3-030-05318-5
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 .A939 2019
245 0 0 $a Automated machine learning $h [electronic resource] : $b methods, systems, challenges / $c edited by Frank Hutter, Lars Kotthoff, Joaquin Vanschoren.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2019.
300 $a xiv, 219 p. : $b ill., digital ; $c 24 cm.
490 1 $a The Springer series on challenges in machine learning, $x 2520-131X
505 0 $a 1 Hyperparameter Optimization -- 2 Meta-Learning -- 3 Neural Architecture Search -- 4 Auto-WEKA -- 5 Hyperopt-Sklearn -- 6 Auto-sklearn -- 7 Towards Automatically-Tuned Deep Neural Networks -- 8 TPOT -- 9 The Automatic Statistician -- 10 AutoML Challenges.
506 $a Open access.
520 $a This open access book presents the first comprehensive overview of general methods in Automated Machine Learning (AutoML), collects descriptions of existing systems based on these methods, and discusses the first series of international challenges of AutoML systems. The recent success of commercial ML applications and the rapid growth of the field has created a high demand for off-the-shelf ML methods that can be used easily and without expert knowledge. However, many of the recent machine learning successes crucially rely on human experts, who manually select appropriate ML architectures (deep learning architectures or more traditional ML workflows) and their hyperparameters. To overcome this problem, the field of AutoML targets a progressive automation of machine learning, based on principles from optimization and machine learning itself. This book serves as a point of entry into this quickly-developing field for researchers and advanced students alike, as well as providing a reference for practitioners aiming to use AutoML in their work.
650 0 $a Machine learning. $3 188639
650 1 4 $a Artificial Intelligence. $3 212515
650 2 4 $a Image Processing and Computer Vision. $3 274051
650 2 4 $a Pattern Recognition. $3 273706
700 1 $a Hutter, Frank. $3 841396
700 1 $a Kotthoff, Lars. $3 841397
700 1 $a Vanschoren, Joaquin. $3 762826
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer eBooks
830 0 $a Springer series on challenges in machine learning. $3 785220
856 4 0 $u https://doi.org/10.1007/978-3-030-05318-5
950 $a Computer Science (Springer-11645)