國立虎尾科技大學 |

Recurrent Neural Networks = From Simple to Gated Architectures /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Recurrent Neural Networks/ by Fathi M. Salem.
Reminder of title:	From Simple to Gated Architectures /
Author:	Salem, Fathi M.
Description:	XX, 121 p. 26 illus., 24 illus. in color.online resource. :
Contained By:	Springer Nature eBook
Subject:	Electronic circuits. -
Online resource:	https://doi.org/10.1007/978-3-030-89929-5
ISBN:	9783030899295

Recurrent Neural Networks = From Simple to Gated Architectures /
Salem, Fathi M.

Recurrent Neural NetworksFrom Simple to Gated Architectures /[electronic resource] :by Fathi M. Salem. - 1st ed. 2022. - XX, 121 p. 26 illus., 24 illus. in color.online resource.

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.

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.

ISBN: 9783030899295

Standard No.: 10.1007/978-3-030-89929-5doiSubjects--Topical Terms:

563332
Electronic circuits.

LC Class. No.: TK7867-7867.5

Dewey Class. No.: 621.3815

Recurrent Neural Networks = From Simple to Gated Architectures /
LDR:03259nam a22003975i 4500 001 1092215
003 DE-He213
005 20220112012414.0
007 cr nn 008mamaa
008 221228s2022 sz | s |||| 0|eng d
020 $a 9783030899295 $9 978-3-030-89929-5
024 7 $a 10.1007/978-3-030-89929-5 $2 doi
035 $a 978-3-030-89929-5
050 4 $a TK7867-7867.5
072 7 $a TJFC $2 bicssc
072 7 $a TEC008010 $2 bisacsh
072 7 $a TJFC $2 thema
082 0 4 $a 621.3815 $2 23
100 1 $a Salem, Fathi M. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1399947
245 1 0 $a Recurrent Neural Networks $h [electronic resource] : $b From Simple to Gated Architectures / $c by Fathi M. Salem.
250 $a 1st ed. 2022.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2022.
300 $a XX, 121 p. 26 illus., 24 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
505 0 $a 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 $a 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 $a Electronic circuits. $3 563332
650 0 $a Signal processing. $3 561459
650 0 $a Data mining. $3 528622
650 1 4 $a Electronic Circuits and Systems. $3 1366689
650 2 4 $a Signal, Speech and Image Processing . $3 1366353
650 2 4 $a Data Mining and Knowledge Discovery. $3 677765
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783030899288
776 0 8 $i Printed edition: $z 9783030899301
776 0 8 $i Printed edition: $z 9783030899318
856 4 0 $u https://doi.org/10.1007/978-3-030-89929-5
912 $a ZDB-2-ENG
912 $a ZDB-2-SXE
950 $a Engineering (SpringerNature-11647)
950 $a Engineering (R0) (SpringerNature-43712)