國立高雄大學圖資館 |

Language: English

Back

A geometric approach to the unificat...

Dong, Tiansi.

A geometric approach to the unification of symbolic structures and neural networks

Record Type:	Electronic resources : Monograph/item
Title/Author:	A geometric approach to the unification of symbolic structures and neural networksby Tiansi Dong.
Author:	Dong, Tiansi.
Published:	Cham :Springer International Publishing :2021.
Description:	xxii, 145 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
Subject:	Neural networks (Computer science)
Online resource:	https://doi.org/10.1007/978-3-030-56275-5
ISBN:	9783030562755$q(electronic bk.)

A geometric approach to the unification of symbolic structures and neural networks
Dong, Tiansi.

A geometric approach to the unification of symbolic structures and neural networks[electronic resource] /by Tiansi Dong. - Cham :Springer International Publishing :2021. - xxii, 145 p. :ill., digital ;24 cm. - Studies in computational intelligence,v.9101860-949X ;. - Studies in computational intelligence ;v. 216..

Introduction -- The Gap between Symbolic and Connectionist Approaches -- Spatializing Symbolic Structures for the Gap -- The Criteria, Challenges, and the Back-Propagation Method -- Design Principles of Geometric Connectionist Machines -- A Geometric Connectionist Machine for Word-Senses -- Geometric Connectionist Machines for Triple Classiﬁcation -- Conclusions & Outlooks.

The unification of symbolist and connectionist models is a major trend in AI. The key is to keep the symbolic semantics unchanged. Unfortunately, present embedding approaches cannot. The approach in this book makes the unification possible. It is indeed a new and promising approach in AI. -Bo Zhang, Director of AI Institute, Tsinghua It is indeed wonderful to see the reviving of the important theme Nural Symbolic Model. Given the popularity and prevalence of deep learning, symbolic processing is often neglected or downplayed. This book confronts this old issue head on, with a historical look, incorporating recent advances and new perspectives, thus leading to promising new methods and approaches. -Ron Sun (RPI), on Governing Board of Cognitive Science Society Both for language and humor, approaches like those described in this book are the way to snickerdoodle wombats. -Christian F. Hempelmann (Texas A&M-Commerce) on Executive Board of International Society for Humor Studies.

ISBN: 9783030562755$q(electronic bk.)

Standard No.: 10.1007/978-3-030-56275-5doiSubjects--Topical Terms:

181982
Neural networks (Computer science)

LC Class. No.: QA76.87 / .D66 2021

Dewey Class. No.: 006.32

A geometric approach to the unification of symbolic structures and neural networks
LDR:02463nmm a2200337 a 4500 001 595142
003 DE-He213
005 20200824205928.0
006 m d
007 cr nn 008maaau
008 211005s2021 sz s 0 eng d
020 $a 9783030562755$q(electronic bk.)
020 $a 9783030562748$q(paper)
024 7 $a 10.1007/978-3-030-56275-5 $2 doi
035 $a 978-3-030-56275-5
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.87 $b .D66 2021
072 7 $a UYQ $2 bicssc
072 7 $a TEC009000 $2 bisacsh
072 7 $a UYQ $2 thema
082 0 4 $a 006.32 $2 23
090 $a QA76.87 $b .D682 2021
100 1 $a Dong, Tiansi. $3 558108
245 1 2 $a A geometric approach to the unification of symbolic structures and neural networks $h [electronic resource] / $c by Tiansi Dong.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2021.
300 $a xxii, 145 p. : $b ill., digital ; $c 24 cm.
490 1 $a Studies in computational intelligence, $x 1860-949X ; $v v.910
505 0 $a Introduction -- The Gap between Symbolic and Connectionist Approaches -- Spatializing Symbolic Structures for the Gap -- The Criteria, Challenges, and the Back-Propagation Method -- Design Principles of Geometric Connectionist Machines -- A Geometric Connectionist Machine for Word-Senses -- Geometric Connectionist Machines for Triple Classiﬁcation -- Conclusions & Outlooks.
520 $a The unification of symbolist and connectionist models is a major trend in AI. The key is to keep the symbolic semantics unchanged. Unfortunately, present embedding approaches cannot. The approach in this book makes the unification possible. It is indeed a new and promising approach in AI. -Bo Zhang, Director of AI Institute, Tsinghua It is indeed wonderful to see the reviving of the important theme Nural Symbolic Model. Given the popularity and prevalence of deep learning, symbolic processing is often neglected or downplayed. This book confronts this old issue head on, with a historical look, incorporating recent advances and new perspectives, thus leading to promising new methods and approaches. -Ron Sun (RPI), on Governing Board of Cognitive Science Society Both for language and humor, approaches like those described in this book are the way to snickerdoodle wombats. -Christian F. Hempelmann (Texas A&M-Commerce) on Executive Board of International Society for Humor Studies.
650 0 $a Neural networks (Computer science) $3 181982
650 0 $a Logic, Symbolic and mathematical. $3 180452
650 1 4 $a Computational Intelligence. $3 338479
650 2 4 $a Machine Learning. $3 833608
650 2 4 $a Mathematical Models of Cognitive Processes and Neural Networks. $3 567118
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a Studies in computational intelligence ; $v v. 216. $3 380871
856 4 0 $u https://doi.org/10.1007/978-3-030-56275-5
950 $a Intelligent Technologies and Robotics (SpringerNature-42732)