Titre :	Deep Learning Architectures : A Mathematical Approach
Type de document :	texte imprimé
Auteurs :	Ovidiu Calin, Auteur
Mention d'édition :	1ère édition
Editeur :	Springer
Année de publication :	2020
Importance :	760 pages
ISBN/ISSN/EAN :	978-3-030-36723-7
Prix :	25670f
Langues :	Français (fre)
Index. décimale :	K.45 Intelligence artificielle et big-data, machine Learning
Résumé :	This book describes how neural networks operate from the mathematical point of view. As a result, neural networks can be interpreted both as function universal approximators and information processors. The book bridges the gap between ideas and concepts of neural networks, which are used nowadays at an intuitive level, and the precise modern mathematical language, presenting the best practices of the former and enjoying the robustness and elegance of the latter. This book can be used in a graduate course in deep learning, with the first few parts being accessible to senior undergraduates. In addition, the book will be of wide interest to machine learning researchers who are interested in a theoretical understanding of the subject.

Deep Learning Architectures : A Mathematical Approach [texte imprimé] / Ovidiu Calin, Auteur  . -  1ère édition . - Springer, 2020 . - 760 pages.
ISBN : 978-3-030-36723-7 : 25670f
Langues : Français (fre)

Index. décimale :

K.45 Intelligence artificielle et big-data, machine Learning

Résumé :

This book describes how neural networks operate from the mathematical point of view. As a result, neural networks can be interpreted both as function universal approximators and information processors. The book bridges the gap between ideas and concepts of neural networks, which are used nowadays at an intuitive level, and the precise modern mathematical language, presenting the best practices of the former and enjoying the robustness and elegance of the latter. This book can be used in a graduate course in deep learning, with the first few parts being accessible to senior undergraduates. In addition, the book will be of wide interest to machine learning researchers who are interested in a theoretical understanding of the subject.