Abstract
This chapter provides a larger perspective and background on the neural blackboard architectures and the underlying theory that have been developed over the last decades. The aim of these is to model compositional 'symbolic' processing, e.g. as found in language, in a neural manner. Neural blackboard architectures achieve this with a form of 'logistics of access' that is different from symbolic architectures. In particular, conceptual representations remain 'in situ' and hence content addressable in any compositional structure of which they are a part. 'Symbolic' processing then consists of the creation and control of temporal connection paths in neural blackboards that possess a 'small world' connection structure. In language, a connection path provides the intrinsic structure of a sentence. In this way, arbitrary sentence structures can be created and processed, and simulations can reproduce and predict brain activity observed in sentence processing. Next to presenting an overview, the chapter will discuss theoretical and modeling foundations and compare them with forms of symbolic processing as found in other AI architectures.
Original language | English |
---|---|
Title of host publication | Compendium of Neurosymbolic Artificial Intelligence |
Publisher | IOS |
Pages | 249-271 |
Number of pages | 23 |
ISBN (Electronic) | 9781643684079 |
ISBN (Print) | 9781643684062 |
DOIs | |
Publication status | Published - 4 Aug 2023 |
Publication series
Name | Frontiers in Artificial Intelligence and Applications |
---|---|
Volume | 369 |
Keywords
- NLA
Fingerprint
Dive into the research topics of 'The neural blackboard theory of neuro-symbolic processing: Logistics of access, connection paths and intrinsic structures'. Together they form a unique fingerprint.
View full fingerprint
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver
van der Velde, F. (2023). The neural blackboard theory of neuro-symbolic processing: Logistics of access, connection paths and intrinsic structures. In Compendium of Neurosymbolic Artificial Intelligence (pp. 249-271). (Frontiers in Artificial Intelligence and Applications; Vol. 369). IOS. https://doi.org/10.3233/FAIA230144
van der Velde, Frank. / The neural blackboard theory of neuro-symbolic processing : Logistics of access, connection paths and intrinsic structures. Compendium of Neurosymbolic Artificial Intelligence. IOS, 2023. pp. 249-271 (Frontiers in Artificial Intelligence and Applications).
@inbook{1a104ab1f91241068e281de1aa4b1162,
title = "The neural blackboard theory of neuro-symbolic processing: Logistics of access, connection paths and intrinsic structures",
abstract = "This chapter provides a larger perspective and background on the neural blackboard architectures and the underlying theory that have been developed over the last decades. The aim of these is to model compositional 'symbolic' processing, e.g. as found in language, in a neural manner. Neural blackboard architectures achieve this with a form of 'logistics of access' that is different from symbolic architectures. In particular, conceptual representations remain 'in situ' and hence content addressable in any compositional structure of which they are a part. 'Symbolic' processing then consists of the creation and control of temporal connection paths in neural blackboards that possess a 'small world' connection structure. In language, a connection path provides the intrinsic structure of a sentence. In this way, arbitrary sentence structures can be created and processed, and simulations can reproduce and predict brain activity observed in sentence processing. Next to presenting an overview, the chapter will discuss theoretical and modeling foundations and compare them with forms of symbolic processing as found in other AI architectures.",
keywords = "NLA",
author = "{van der Velde}, Frank",
note = "Publisher Copyright: {\textcopyright} 2023 The authors and IOS Press. All rights reserved.",
year = "2023",
month = aug,
day = "4",
doi = "10.3233/FAIA230144",
language = "English",
isbn = "9781643684062",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS",
pages = "249--271",
booktitle = "Compendium of Neurosymbolic Artificial Intelligence",
address = "Netherlands",
}
van der Velde, F 2023, The neural blackboard theory of neuro-symbolic processing: Logistics of access, connection paths and intrinsic structures. in Compendium of Neurosymbolic Artificial Intelligence. Frontiers in Artificial Intelligence and Applications, vol. 369, IOS, pp. 249-271. https://doi.org/10.3233/FAIA230144
The neural blackboard theory of neuro-symbolic processing: Logistics of access, connection paths and intrinsic structures. / van der Velde, Frank.
Compendium of Neurosymbolic Artificial Intelligence. IOS, 2023. p. 249-271 (Frontiers in Artificial Intelligence and Applications; Vol. 369).
Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review
TY - CHAP
T1 - The neural blackboard theory of neuro-symbolic processing
T2 - Logistics of access, connection paths and intrinsic structures
AU - van der Velde, Frank
N1 - Publisher Copyright:© 2023 The authors and IOS Press. All rights reserved.
PY - 2023/8/4
Y1 - 2023/8/4
N2 - This chapter provides a larger perspective and background on the neural blackboard architectures and the underlying theory that have been developed over the last decades. The aim of these is to model compositional 'symbolic' processing, e.g. as found in language, in a neural manner. Neural blackboard architectures achieve this with a form of 'logistics of access' that is different from symbolic architectures. In particular, conceptual representations remain 'in situ' and hence content addressable in any compositional structure of which they are a part. 'Symbolic' processing then consists of the creation and control of temporal connection paths in neural blackboards that possess a 'small world' connection structure. In language, a connection path provides the intrinsic structure of a sentence. In this way, arbitrary sentence structures can be created and processed, and simulations can reproduce and predict brain activity observed in sentence processing. Next to presenting an overview, the chapter will discuss theoretical and modeling foundations and compare them with forms of symbolic processing as found in other AI architectures.
AB - This chapter provides a larger perspective and background on the neural blackboard architectures and the underlying theory that have been developed over the last decades. The aim of these is to model compositional 'symbolic' processing, e.g. as found in language, in a neural manner. Neural blackboard architectures achieve this with a form of 'logistics of access' that is different from symbolic architectures. In particular, conceptual representations remain 'in situ' and hence content addressable in any compositional structure of which they are a part. 'Symbolic' processing then consists of the creation and control of temporal connection paths in neural blackboards that possess a 'small world' connection structure. In language, a connection path provides the intrinsic structure of a sentence. In this way, arbitrary sentence structures can be created and processed, and simulations can reproduce and predict brain activity observed in sentence processing. Next to presenting an overview, the chapter will discuss theoretical and modeling foundations and compare them with forms of symbolic processing as found in other AI architectures.
KW - NLA
UR - http://www.scopus.com/inward/record.url?scp=85172816875&partnerID=8YFLogxK
U2 - 10.3233/FAIA230144
DO - 10.3233/FAIA230144
M3 - Chapter
AN - SCOPUS:85172816875
SN - 9781643684062
T3 - Frontiers in Artificial Intelligence and Applications
SP - 249
EP - 271
BT - Compendium of Neurosymbolic Artificial Intelligence
PB - IOS
ER -
van der Velde F. The neural blackboard theory of neuro-symbolic processing: Logistics of access, connection paths and intrinsic structures. In Compendium of Neurosymbolic Artificial Intelligence. IOS. 2023. p. 249-271. (Frontiers in Artificial Intelligence and Applications). doi: 10.3233/FAIA230144