MARC details
000 -LEADER |
fixed length control field |
03586nam a22004935i 4500 |
003 - CONTROL NUMBER IDENTIFIER |
control field |
TR-AnTOB |
005 - DATE AND TIME OF LATEST TRANSACTION |
control field |
20231124085953.0 |
007 - PHYSICAL DESCRIPTION FIXED FIELD--GENERAL INFORMATION |
fixed length control field |
cr nn 008mamaa |
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
fixed length control field |
220103s2022 sz | s |||| 0|eng d |
020 ## - INTERNATIONAL STANDARD BOOK NUMBER |
International Standard Book Number |
9783030899295 |
024 7# - OTHER STANDARD IDENTIFIER |
Standard number or code |
10.1007/978-3-030-89929-5 |
Source of number or code |
doi |
040 ## - CATALOGING SOURCE |
Original cataloging agency |
TR-AnTOB |
Language of cataloging |
eng |
Description conventions |
rda |
Transcribing agency |
TR-AnTOB |
041 ## - LANGUAGE CODE |
Language code of text/sound track or separate title |
İngilizce |
050 #4 - LIBRARY OF CONGRESS CALL NUMBER |
Classification number |
TK7867 |
072 #7 - SUBJECT CATEGORY CODE |
Subject category code |
TJFC |
Source |
bicssc |
|
Subject category code |
TEC008010 |
Source |
bisacsh |
|
Subject category code |
TJFC |
Source |
thema |
090 ## - LOCALLY ASSIGNED LC-TYPE CALL NUMBER (OCLC); LOCAL CALL NUMBER (RLIN) |
Classification number (OCLC) (R) ; Classification number, CALL (RLIN) (NR) |
TK7867EBK |
100 1# - MAIN ENTRY--PERSONAL NAME |
Personal name |
Salem, Fathi M. |
Relator term |
author. |
Relator code |
aut |
-- |
http://id.loc.gov/vocabulary/relators/aut |
245 10 - TITLE STATEMENT |
Title |
Recurrent Neural Networks |
Medium |
[electronic resource] : |
Remainder of title |
From Simple to Gated Architectures / |
Statement of responsibility, etc. |
by Fathi M. Salem. |
250 ## - EDITION STATEMENT |
Edition statement |
1st ed. 2022. |
264 #1 - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE |
Place of production, publication, distribution, manufacture |
Cham : |
Name of producer, publisher, distributor, manufacturer |
Springer International Publishing : |
-- |
Imprint: Springer, |
Date of production, publication, distribution, manufacture, or copyright notice |
2022. |
300 ## - PHYSICAL DESCRIPTION |
Extent |
1 online resource |
336 ## - CONTENT TYPE |
Content type term |
text |
Content type code |
txt |
Source |
rdacontent |
337 ## - MEDIA TYPE |
Media type term |
computer |
Media type code |
c |
Source |
rdamedia |
338 ## - CARRIER TYPE |
Carrier type term |
online resource |
Carrier type code |
cr |
Source |
rdacarrier |
347 ## - DIGITAL FILE CHARACTERISTICS |
File type |
text file |
Encoding format |
PDF |
Source |
rda |
505 0# - FORMATTED CONTENTS NOTE |
Formatted contents note |
Introduction -- 1. Network Architectures -- 2. Learning Processes -- 3. Recurrent Neural Networks (RNN) -- 4. Gated RNN: The Long Short-Term Memory (LSTM) RNN -- 5. Gated RNN: The Gated Recurrent Unit (GRU) RNN -- 6. Gated RNN: The Minimal Gated Unit (MGU) RNN. |
520 ## - SUMMARY, ETC. |
Summary, etc. |
This textbook provides a compact but comprehensive treatment that provides analytical and design steps to recurrent neural networks from scratch. It provides a treatment of the general recurrent neural networks with principled methods for training that render the (generalized) backpropagation through time (BPTT). This author focuses on the basics and nuances of recurrent neural networks, providing technical and principled treatment of the subject, with a view toward using coding and deep learning computational frameworks, e.g., Python and Tensorflow-Keras. Recurrent neural networks are treated holistically from simple to gated architectures, adopting the technical machinery of adaptive non-convex optimization with dynamic constraints to leverage its systematic power in organizing the learning and training processes. This permits the flow of concepts and techniques that provide grounded support for design and training choices. The author’s approach enables strategic co-training of output layers, using supervised learning, and hidden layers, using unsupervised learning, to generate more efficient internal representations and accuracy performance. As a result, readers will be enabled to create designs tailoring proficient procedures for recurrent neural networks in their targeted applications. Explains the intricacy and diversity of recurrent networks from simple to more complex gated recurrent neural networks; Discusses the design framing of such networks, and how to redesign simple RNN to avoid unstable behavior; Describes the forms of training of RNNs framed in adaptive non-convex optimization with dynamics constraints. |
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM |
Topical term or geographic name entry element |
Electronic circuits. |
|
Topical term or geographic name entry element |
Signal processing. |
|
Topical term or geographic name entry element |
Data mining. |
|
Topical term or geographic name entry element |
Electronic Circuits and Systems. |
|
Topical term or geographic name entry element |
Signal, Speech and Image Processing . |
|
Topical term or geographic name entry element |
Data Mining and Knowledge Discovery. |
653 ## - INDEX TERM--UNCONTROLLED |
Uncontrolled term |
Neural networks (Computer science) |
710 2# - ADDED ENTRY--CORPORATE NAME |
Corporate name or jurisdiction name as entry element |
SpringerLink (Online service) |
856 40 - ELECTRONIC LOCATION AND ACCESS |
Uniform Resource Identifier |
<a href="https://doi.org/10.1007/978-3-030-89929-5">https://doi.org/10.1007/978-3-030-89929-5</a> |
Materials specified |
Springer eBooks |
Public note |
Online access link to the resource |
942 ## - ADDED ENTRY ELEMENTS (KOHA) |
Source of classification or shelving scheme |
Library of Congress Classification |
Koha item type |
E-Book |