東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Deep learning architectures = a math...

Calin, Ovidiu.

Linked to FindBook

Google Book

Amazon

博客來

Deep learning architectures = a mathematical approach /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deep learning architectures/ by Ovidiu Calin.
Reminder of title:	a mathematical approach /
Author:	Calin, Ovidiu.
Published:	Cham :Springer International Publishing : : 2020.,
Description:	xxx, 760 p. :ill., digital ;24 cm.
[NT 15003449]:	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.
Contained By:	Springer eBooks
Subject:	Machine learning - Mathematics. -
Online resource:	https://doi.org/10.1007/978-3-030-36721-3
ISBN:	9783030367213

Deep learning architectures = a mathematical approach /
Calin, Ovidiu.

Deep learning architecturesa mathematical approach /[electronic resource] :by Ovidiu Calin. - Cham :Springer International Publishing :2020. - xxx, 760 p. :ill., digital ;24 cm. - Springer series in the data sciences,2365-5674. - Springer series in the data sciences..

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.

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.

ISBN: 9783030367213

Standard No.: 10.1007/978-3-030-36721-3doiSubjects--Topical Terms:

3442737
Machine learning
--Mathematics.

LC Class. No.: Q325.5 / .C355 2020

Dewey Class. No.: 006.310151

Deep learning architectures = a mathematical approach /
LDR:02276nmm a2200337 a 4500 001 2216478
003 DE-He213
005 20200721150354.0
006 m d
007 cr nn 008maaau
008 201120s2020 sz s 0 eng d
020 $a 9783030367213 $q (electronic bk.)
020 $a 9783030367206 $q (paper)
024 7 $a 10.1007/978-3-030-36721-3 $2 doi
035 $a 978-3-030-36721-3
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.5 $b .C355 2020
072 7 $a PBWH $2 bicssc
072 7 $a MAT003000 $2 bisacsh
072 7 $a PBWH $2 thema
082 0 4 $a 006.310151 $2 23
090 $a Q325.5 $b .C154 2020
100 1 $a Calin, Ovidiu. $3 897381
245 1 0 $a Deep learning architectures $h [electronic resource] : $b a mathematical approach / $c by Ovidiu Calin.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a xxx, 760 p. : $b ill., digital ; $c 24 cm.
490 1 $a Springer series in the data sciences, $x 2365-5674
505 0 $a 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.
520 $a 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.
650 0 $a Machine learning $x Mathematics. $3 3442737
650 1 4 $a Mathematical Applications in Computer Science. $3 1567978
650 2 4 $a Machine Learning. $3 3382522
710 2 $a SpringerLink (Online service) $3 836513
773 0 $t Springer eBooks
830 0 $a Springer series in the data sciences. $3 2165646
856 4 0 $u https://doi.org/10.1007/978-3-030-36721-3
950 $a Mathematics and Statistics (Springer-11649)