國立虎尾科技大學 |

Random matrix methods for machine learning /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Random matrix methods for machine learning // Romain Couillet, Grenoble Alpes University, Zhenyu Liao, Huazhong University of Science and Technology.
Author:	Couillet, Romain,
other author:	Liao, Zhenyu,
Description:	1 online resource (vi, 402 pages) :digital, PDF file(s). :
Notes:	Title from publisher's bibliographic system (viewed on 30 Jun 2022).
Subject:	Machine learning - Mathematics. -
Online resource:	https://doi.org/10.1017/9781009128490
ISBN:	9781009128490 (ebook)

Random matrix methods for machine learning /
Couillet, Romain,1983-

Random matrix methods for machine learning /Romain Couillet, Grenoble Alpes University, Zhenyu Liao, Huazhong University of Science and Technology. - 1 online resource (vi, 402 pages) :digital, PDF file(s).

Title from publisher's bibliographic system (viewed on 30 Jun 2022).

This book presents a unified theory of random matrices for applications in machine learning, offering a large-dimensional data vision that exploits concentration and universality phenomena. This enables a precise understanding, and possible improvements, of the core mechanisms at play in real-world machine learning algorithms. The book opens with a thorough introduction to the theoretical basics of random matrices, which serves as a support to a wide scope of applications ranging from SVMs, through semi-supervised learning, unsupervised spectral clustering, and graph methods, to neural networks and deep learning. For each application, the authors discuss small- versus large-dimensional intuitions of the problem, followed by a systematic random matrix analysis of the resulting performance and possible improvements. All concepts, applications, and variations are illustrated numerically on synthetic as well as real-world data, with MATLAB and Python code provided on the accompanying website.

ISBN: 9781009128490 (ebook)Subjects--Topical Terms:

1340126
Machine learning
--Mathematics.

LC Class. No.: Q325.5 / .C69 2022

Dewey Class. No.: 006.31

Random matrix methods for machine learning /
LDR:02069nam a2200277 i 4500 001 1124549
003 UkCbUP
005 20220704121753.0
006 m|||||o||d||||||||
007 cr||||||||||||
008 240926s2022||||enk o ||1 0|eng|d
020 $a 9781009128490 (ebook)
020 $z 9781009123235 (hardback)
035 $a CR9781009128490
040 $a UkCbUP $b eng $e rda $c UkCbUP
050 0 0 $a Q325.5 $b .C69 2022
082 0 4 $a 006.31 $2 23
100 1 $a Couillet, Romain, $d 1983- $e author. $3 1442151
245 1 0 $a Random matrix methods for machine learning / $c Romain Couillet, Grenoble Alpes University, Zhenyu Liao, Huazhong University of Science and Technology.
264 1 $a Cambridge, United Kingdom ; New York, NY, USA : $b Cambridge University Press, $c 2022.
300 $a 1 online resource (vi, 402 pages) : $b digital, PDF file(s).
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Title from publisher's bibliographic system (viewed on 30 Jun 2022).
520 $a This book presents a unified theory of random matrices for applications in machine learning, offering a large-dimensional data vision that exploits concentration and universality phenomena. This enables a precise understanding, and possible improvements, of the core mechanisms at play in real-world machine learning algorithms. The book opens with a thorough introduction to the theoretical basics of random matrices, which serves as a support to a wide scope of applications ranging from SVMs, through semi-supervised learning, unsupervised spectral clustering, and graph methods, to neural networks and deep learning. For each application, the authors discuss small- versus large-dimensional intuitions of the problem, followed by a systematic random matrix analysis of the resulting performance and possible improvements. All concepts, applications, and variations are illustrated numerically on synthetic as well as real-world data, with MATLAB and Python code provided on the accompanying website.
650 0 $a Machine learning $x Mathematics. $3 1340126
650 0 $a Matrix analytic methods. $3 1019605
700 1 $a Liao, Zhenyu, $d 1992- $e author. $3 1442152
776 0 8 $i Print version: $z 9781009123235
856 4 0 $u https://doi.org/10.1017/9781009128490