Cargando…

Deep learning architectures: a mathematical approach

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...

Descripción completa

Detalles Bibliográficos
Autor principal: Calin, Ovidiu
Lenguaje:eng
Publicado: Springer 2020
Materias:
Acceso en línea:https://dx.doi.org/10.1007/978-3-030-36721-3
http://cds.cern.ch/record/2713881
_version_ 1780965364025262080
author Calin, Ovidiu
author_facet Calin, Ovidiu
author_sort Calin, Ovidiu
collection CERN
description 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. .
id cern-2713881
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2020
publisher Springer
record_format invenio
spelling cern-27138812021-04-21T18:09:06Zdoi:10.1007/978-3-030-36721-3http://cds.cern.ch/record/2713881engCalin, OvidiuDeep learning architectures: a mathematical approachMathematical Physics and MathematicsThis 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. .Springeroai:cds.cern.ch:27138812020
spellingShingle Mathematical Physics and Mathematics
Calin, Ovidiu
Deep learning architectures: a mathematical approach
title Deep learning architectures: a mathematical approach
title_full Deep learning architectures: a mathematical approach
title_fullStr Deep learning architectures: a mathematical approach
title_full_unstemmed Deep learning architectures: a mathematical approach
title_short Deep learning architectures: a mathematical approach
title_sort deep learning architectures: a mathematical approach
topic Mathematical Physics and Mathematics
url https://dx.doi.org/10.1007/978-3-030-36721-3
http://cds.cern.ch/record/2713881
work_keys_str_mv AT calinovidiu deeplearningarchitecturesamathematicalapproach