國立高雄大學圖資館 |

Language: English

Back

The geometry of intelligencefoundations of transformer networks in deep learning /

Record Type:	Electronic resources : Monograph/item
Title/Author:	The geometry of intelligenceby Pradeep Singh, Balasubramanian Raman.
Reminder of title:	foundations of transformer networks in deep learning /
Author:	Singh, Pradeep.
other author:	Raman, Balasubramanian.
Published:	Singapore :Springer Nature Singapore :2025.
Description:	xxi, 361 p. :ill. (some col.), digital ;24 cm.
Contained By:	Springer Nature eBook
Subject:	Artificial intelligenceMathematics.
Online resource:	https://doi.org/10.1007/978-981-96-4706-4
ISBN:	9789819647064$q(electronic bk.)

The geometry of intelligencefoundations of transformer networks in deep learning /
Singh, Pradeep.

The geometry of intelligencefoundations of transformer networks in deep learning /[electronic resource] :by Pradeep Singh, Balasubramanian Raman. - Singapore :Springer Nature Singapore :2025. - xxi, 361 p. :ill. (some col.), digital ;24 cm. - Studies in big data,v. 1752197-6511 ;. - Studies in big data ;v.1..

Foundations of Representation Theory in Transformers -- Word Embeddings and Positional Encoding -- Attention Mechanisms -- Transformer Architecture: Encoder and Decoder -- Transformers in Natural Language Processing -- Transformers in Computer Vision -- Time Series Forecasting with Transformers -- Signal Analysis and Transformers -- Advanced Topics and Future Directions -- Convergence of Transformer Models: A Dynamical Systems Perspective.

This book offers an in-depth exploration of the mathematical foundations underlying transformer networks, the cornerstone of modern AI across various domains. Unlike existing literature that focuses primarily on implementation, this work delves into the elegant geometry, symmetry, and mathematical structures that drive the success of transformers. Through rigorous analysis and theoretical insights, the book unravels the complex relationships and dependencies that these models capture, providing a comprehensive understanding of their capabilities. Designed for researchers, academics, and advanced practitioners, this text bridges the gap between practical application and theoretical exploration. Readers will gain a profound understanding of how transformers operate in abstract spaces, equipping them with the knowledge to innovate, optimize, and push the boundaries of AI. Whether you seek to deepen your expertise or pioneer the next generation of AI models, this book is an essential resource on the mathematical principles of transformers.

ISBN: 9789819647064$q(electronic bk.)

Standard No.: 10.1007/978-981-96-4706-4doiSubjects--Topical Terms:

324997
Artificial intelligence
--Mathematics.

LC Class. No.: Q335

Dewey Class. No.: 006.30151

The geometry of intelligencefoundations of transformer networks in deep learning /
LDR:02602nmm a2200337 a 4500 001 678046
003 DE-He213
005 20250522130240.0
006 m d
007 cr nn 008maaau
008 251021s2025 si s 0 eng d
020 $a 9789819647064$q(electronic bk.)
020 $a 9789819647057$q(paper)
024 7 $a 10.1007/978-981-96-4706-4 $2 doi
035 $a 978-981-96-4706-4
040 $a GP $c GP
041 0 $a eng
050 4 $a Q335
072 7 $a UYQ $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQ $2 thema
082 0 4 $a 006.30151 $2 23
090 $a Q335 $b .S617 2025
100 1 $a Singh, Pradeep. $3 944511
245 1 4 $a The geometry of intelligence $h [electronic resource] : $b foundations of transformer networks in deep learning / $c by Pradeep Singh, Balasubramanian Raman.
260 $a Singapore : $b Springer Nature Singapore : $b Imprint: Springer, $c 2025.
300 $a xxi, 361 p. : $b ill. (some col.), digital ; $c 24 cm.
490 1 $a Studies in big data, $x 2197-6511 ; $v v. 175
505 0 $a Foundations of Representation Theory in Transformers -- Word Embeddings and Positional Encoding -- Attention Mechanisms -- Transformer Architecture: Encoder and Decoder -- Transformers in Natural Language Processing -- Transformers in Computer Vision -- Time Series Forecasting with Transformers -- Signal Analysis and Transformers -- Advanced Topics and Future Directions -- Convergence of Transformer Models: A Dynamical Systems Perspective.
520 $a This book offers an in-depth exploration of the mathematical foundations underlying transformer networks, the cornerstone of modern AI across various domains. Unlike existing literature that focuses primarily on implementation, this work delves into the elegant geometry, symmetry, and mathematical structures that drive the success of transformers. Through rigorous analysis and theoretical insights, the book unravels the complex relationships and dependencies that these models capture, providing a comprehensive understanding of their capabilities. Designed for researchers, academics, and advanced practitioners, this text bridges the gap between practical application and theoretical exploration. Readers will gain a profound understanding of how transformers operate in abstract spaces, equipping them with the knowledge to innovate, optimize, and push the boundaries of AI. Whether you seek to deepen your expertise or pioneer the next generation of AI models, this book is an essential resource on the mathematical principles of transformers.
650 0 $a Artificial intelligence $x Mathematics. $3 324997
650 0 $a Transformations (Mathematics) $3 182635
650 1 4 $a Computational Intelligence. $3 338479
650 2 4 $a Artificial Intelligence. $3 212515
650 2 4 $a Communications Engineering, Networks. $3 273745
650 2 4 $a Machine Learning. $3 833608
700 1 $a Raman, Balasubramanian. $3 772227
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a Studies in big data ; $v v.1. $3 675357
856 4 0 $u https://doi.org/10.1007/978-981-96-4706-4
950 $a Intelligent Technologies and Robotics (SpringerNature-42732)