Shortcuts
Please wait while page loads.
SISSA Library . Default .
PageMenu- Main Menu-
Page content

Catalogue Display

Deep Learning Architectures: A Mathematical Approach

Deep Learning Architectures: A Mathematical Approach
Catalogue Information
Field name Details
Dewey Class 004.0151
Title Deep Learning Architectures ([EBook]) : A Mathematical Approach / / by Ovidiu Calin.
Author Calin, Ovidiu
Other name(s) SpringerLink (Online service)
Edition statement 1st ed. 2020.
Publication Cham : : Springer International Publishing : : Imprint: Springer, , 2020.
Physical Details XXX, 760 p. 213 illus., 35 illus. in color. : online resource.
Series Springer Series in the Data Sciences 2365-5674
ISBN 9783030367213
Summary Note 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. .:
Contents note Introductory Problems -- Activation Functions -- Cost Functions -- Finding Minima Algorithms -- Abstract Neurons -- Neural Networks -- Approximation Theorems -- Learning with One-dimensional Inputs -- Universal Approximators -- Exact Learning -- Information Representation -- Information Capacity Assessment -- Output Manifolds -- Neuromanifolds -- Pooling -- Convolutional Networks -- Recurrent Neural Networks -- Classification -- Generative Models -- Stochastic Networks -- Hints and Solutions. .
Mode of acces to digital resource Digital book. Cham Springer Nature 2020. - Mode of access: World Wide Web. System requirements: Internet Explorer 6.0 (or higher) or Firefox 2.0 (or higher). Available as searchable text in PDF format
System details note - Online access to this digital book is restricted to subscription institutions through IP address (only for SISSA internal users).
Internet Site https://doi.org/10.1007/978-3-030-36721-3
Links to Related Works
Subject References:
Authors:
Corporate Authors:
Series:
Classification:
Catalogue Information 50371 Beginning of record . Catalogue Information 50371 Top of page .

Reviews


This item has not been rated.    Add a Review and/or Rating50371
Quick Search