A Geometric Approach to the Unification of Symbolic Structures and Neural Networks
Authors: Dong, Tiansi
Free Preview- Presents a Geometric Approach to The Unification of Symbolic Structures and Neural Networks
- Presents an up-to-date (as well as historical) look at the symbolic processing
- Incorporates recent advances and new perspectives, thus leading to promising new methods and new approaches
Buy this book
- About this book
-
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
- Table of contents (9 chapters)
-
-
Introduction
Pages 1-15
-
The Gap Between Symbolic and Connectionist Approaches
Pages 17-29
-
Spatializing Symbolic Structures for the Gap
Pages 31-41
-
The Criteria, Challenges, and the Back-Propagation Method
Pages 43-60
-
Design Principles of Geometric Connectionist Machines
Pages 61-71
-
Table of contents (9 chapters)
Recommended for you
Bibliographic Information
- Bibliographic Information
-
- Book Title
- A Geometric Approach to the Unification of Symbolic Structures and Neural Networks
- Authors
-
- Tiansi Dong
- Series Title
- Studies in Computational Intelligence
- Series Volume
- 910
- Copyright
- 2021
- Publisher
- Springer International Publishing
- Copyright Holder
- The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
- eBook ISBN
- 978-3-030-56275-5
- DOI
- 10.1007/978-3-030-56275-5
- Hardcover ISBN
- 978-3-030-56274-8
- Series ISSN
- 1860-949X
- Edition Number
- 1
- Number of Pages
- XXII, 145
- Number of Illustrations
- 103 b/w illustrations, 45 illustrations in colour
- Topics
