國立高雄大學圖資館 |

登入

回首頁

Recurrent neural networksfrom simple to gated architectures /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Recurrent neural networksby Fathi M. Salem.
其他題名:	from simple to gated architectures /
作者:	Salem, Fathi M.
出版者:	Cham :Springer International Publishing :2022.
面頁冊數:	xx, 121 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
標題:	Neural networks (Computer science)
電子資源:	https://doi.org/10.1007/978-3-030-89929-5
ISBN:	9783030899295$q(electronic bk.)

Recurrent neural networksfrom simple to gated architectures /
Salem, Fathi M.

Recurrent neural networksfrom simple to gated architectures /[electronic resource] :by Fathi M. Salem. - Cham :Springer International Publishing :2022. - xx, 121 p. :ill., digital ;24 cm.

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 layered, 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$q(electronic bk.)

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

181982
Neural networks (Computer science)

LC Class. No.: QA76.87 / .S35 2022

Dewey Class. No.: 006.32

Recurrent neural networksfrom simple to gated architectures /
LDR:02886nmm a2200325 a 4500 001 619323
003 DE-He213
005 20220103195025.0
006 m d
007 cr nn 008maaau
008 221103s2022 sz s 0 eng d
020 $a 9783030899295$q(electronic bk.)
020 $a 9783030899288$q(paper)
024 7 $a 10.1007/978-3-030-89929-5 $2 doi
035 $a 978-3-030-89929-5
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.87 $b .S35 2022
072 7 $a TJFC $2 bicssc
072 7 $a TEC008010 $2 bisacsh
072 7 $a TJFC $2 thema
082 0 4 $a 006.32 $2 23
090 $a QA76.87 $b .S163 2022
100 1 $a Salem, Fathi M. $3 919537
245 1 0 $a Recurrent neural networks $h [electronic resource] : $b from simple to gated architectures / $c by Fathi M. Salem.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2022.
300 $a xx, 121 p. : $b ill., digital ; $c 24 cm.
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 layered, 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 Neural networks (Computer science) $3 181982
650 1 4 $a Circuits and Systems. $3 274416
650 2 4 $a Signal, Image and Speech Processing. $3 273768
650 2 4 $a Data Mining and Knowledge Discovery. $3 275288
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-3-030-89929-5
950 $a Engineering (SpringerNature-11647)