Automated Machine Learning : Methods, Systems, Challenges

Saved in:
Bibliographic Details
Corporate Author:
Other Authors:
Special Collection:e-book
Format: Book
Language:English
Published: Cham : Springer International Publishing, 2019
Series:The Springer Series on Challenges in Machine Learning, ISSN 2520-131X
Subjects:
Online Access:http://doi.org/10.1007/978-3-030-05318-5
Tags: Add Tag
Be the first to tag this record!
LEADER nam a22 c 4500
001 001012984
005 20210413152323.0
007 cr nn 008mamaa
008 190517s2019 gw adf fsb 000 0 eng d
020 |a 978-3-030-05318-5 
024 7 |a 10.1007/978-3-030-05318-5  |2 doi 
040 |a Springer  |b hun  |d ELTE 
041 0 |a eng 
050 4 |a Q334-342 
082 0 4 |a 006.3  |2 23 
245 0 0 |a Automated Machine Learning  |b Methods, Systems, Challenges  |c edited by Frank Hutter, Lars Kotthoff, Joaquin Vanschoren. 
260 |a Cham  |b Springer International Publishing  |c 2019 
300 |a XIV, 219 p. 54 illusztrált, 45 illusztrált szinesben  |b online forrás 
336 |a szöveg  |b txt  |2 rdacontent 
337 |a számítógépes  |b c  |2 rdamedia 
338 |a távoli hozzáférés  |b cr  |2 rdacarrier 
347 |a szövegfájl  |b PDF  |2 rda 
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. 
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. 
580 |a Nyomtatott kiadás: ISBN 9783030053178 
580 |a Nyomtatott kiadás: ISBN 9783030053192 
506 |a Az e-könyvek a teljes ELTE IP-tartományon belül online elérhetők. 
595 |a e-book 
598 |a könyv 
650 0 4 |a optikai adatfeldolgozás 
650 0 4 |a alakfelismerés 
650 0 |a Artificial intelligence. 
650 0 |a Optical data processing. 
650 0 |a Pattern recognition. 
653 |a elektronikus könyv 
700 1 |a Hutter, Frank  |e szerk. 
700 1 |a Kotthoff, Lars  |e szerk. 
700 1 |a Vanschoren, Joaquin  |e szerk. 
710 2 |a SpringerLink (Online service)  |e közreadó testület 
830 0 |a The Springer Series on Challenges in Machine Learning 
856 4 0 |y Online változat  |u http://doi.org/10.1007/978-3-030-05318-5 
850 |a B2 
264 1 |a Cham  |b Springer International Publishing  |b Imprint: Springer,  |c 2019