國立虎尾科技大學 |

The principles of deep learning theory = an effective theory approach to understanding neural networks /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	The principles of deep learning theory/ Daniel A. Roberts, Sho Yaida based on research in collaboration with Boris Hanin.
Reminder of title:	an effective theory approach to understanding neural networks /
Author:	Roberts, Daniel A.
other author:	Hanin, Boris,
Published:	Cambridge :Cambridge University Press, : 2022.,
Description:	x, 460 p. :ill., digital ; : 26 cm.;
Notes:	Title from publisher's bibliographic system (viewed on 07 Apr 2022).
Subject:	Deep learning (Machine learning) -
Online resource:	https://doi.org/10.1017/9781009023405
ISBN:	9781009023405

The principles of deep learning theory = an effective theory approach to understanding neural networks /
Roberts, Daniel A.

The principles of deep learning theoryan effective theory approach to understanding neural networks /[electronic resource] :Daniel A. Roberts, Sho Yaida based on research in collaboration with Boris Hanin. - Cambridge :Cambridge University Press,2022. - x, 460 p. :ill., digital ;26 cm.

Title from publisher's bibliographic system (viewed on 07 Apr 2022).

This textbook establishes a theoretical framework for understanding deep learning models of practical relevance. With an approach that borrows from theoretical physics, Roberts and Yaida provide clear and pedagogical explanations of how realistic deep neural networks actually work. To make results from the theoretical forefront accessible, the authors eschew the subject's traditional emphasis on intimidating formality without sacrificing accuracy. Straightforward and approachable, this volume balances detailed first-principle derivations of novel results with insight and intuition for theorists and practitioners alike. This self-contained textbook is ideal for students and researchers interested in artificial intelligence with minimal prerequisites of linear algebra, calculus, and informal probability theory, and it can easily fill a semester-long course on deep learning theory. For the first time, the exciting practical advances in modern artificial intelligence capabilities can be matched with a set of effective principles, providing a timeless blueprint for theoretical research in deep learning.

ISBN: 9781009023405Subjects--Topical Terms:

1381171
Deep learning (Machine learning)

LC Class. No.: Q325.73 / .R63 2022

Dewey Class. No.: 006.31

The principles of deep learning theory = an effective theory approach to understanding neural networks /
LDR:02032nam a2200241 a 4500 001 1096528
003 UkCbUP
005 20220511154029.0
006 m d
007 cr nn 008maaau
008 221229s2022 enk o 1 0 eng d
020 $a 9781009023405 $q (electronic bk.)
020 $a 9781316519332 $q (hardback)
035 $a CR9781009023405
040 $a UkCbUP $b eng $c UkCbUP $d GP
050 0 0 $a Q325.73 $b .R63 2022
082 0 0 $a 006.31 $2 23
090 $a Q325.73 $b .R643 2022
100 1 $a Roberts, Daniel A. $3 1405728
245 1 4 $a The principles of deep learning theory $h [electronic resource] : $b an effective theory approach to understanding neural networks / $c Daniel A. Roberts, Sho Yaida based on research in collaboration with Boris Hanin.
260 $a Cambridge : $b Cambridge University Press, $c 2022.
300 $a x, 460 p. : $b ill., digital ; $c 26 cm.
500 $a Title from publisher's bibliographic system (viewed on 07 Apr 2022).
520 $a This textbook establishes a theoretical framework for understanding deep learning models of practical relevance. With an approach that borrows from theoretical physics, Roberts and Yaida provide clear and pedagogical explanations of how realistic deep neural networks actually work. To make results from the theoretical forefront accessible, the authors eschew the subject's traditional emphasis on intimidating formality without sacrificing accuracy. Straightforward and approachable, this volume balances detailed first-principle derivations of novel results with insight and intuition for theorists and practitioners alike. This self-contained textbook is ideal for students and researchers interested in artificial intelligence with minimal prerequisites of linear algebra, calculus, and informal probability theory, and it can easily fill a semester-long course on deep learning theory. For the first time, the exciting practical advances in modern artificial intelligence capabilities can be matched with a set of effective principles, providing a timeless blueprint for theoretical research in deep learning.
650 0 $a Deep learning (Machine learning) $3 1381171
700 1 $a Hanin, Boris, $e collaborator. $3 1405730
700 1 $a Yaida, Sho. $3 1405729
856 4 0 $u https://doi.org/10.1017/9781009023405