Distributed associative memories for high-speed symbolic reasoning

J Austin

doi:10.1016/0165-0114(95)00258-8

Distributed associative memories for high-speed symbolic reasoning

J Austin

Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

This paper briefly introduces a novel symbolic reasoning system based upon distributed associative memories which are constructed from correlation matrix memories (CMM). The system is aimed at high-speed rule-based symbolic operations. It has the advantage of very fast rule matching without the long training times normally associated with neural-network-based symbolic manipulation systems. In particular, the network is able to perform partial matching on symbolic information at high speed. As such, the system is aimed at the practical use of neural networks in high-speed reasoning systems. The paper describes the advantages and disadvantages of using CMM and shows how the approach overcomes those disadvantages. It then briefly describes a system incorporating CMM.

Original language	English
Pages (from-to)	223-233
Number of pages	11
Journal	Fuzzy Sets and Systems
Volume	82
Issue number	2
DOIs	https://doi.org/10.1016/0165-0114(95)00258-8
Publication status	Published - 9 Sept 1996

Bibliographical note

Keywords

neural networks
associative memory
superimposed coding
rule-based systems

Access to Document

10.1016/0165-0114(95)00258-8

austinj18.pdf

http://dx.doi.org/10.1016/0165-0114(95)00258-8

Cite this

@article{625533abc840419fa79de68a24d30513,

title = "Distributed associative memories for high-speed symbolic reasoning",

abstract = "This paper briefly introduces a novel symbolic reasoning system based upon distributed associative memories which are constructed from correlation matrix memories (CMM). The system is aimed at high-speed rule-based symbolic operations. It has the advantage of very fast rule matching without the long training times normally associated with neural-network-based symbolic manipulation systems. In particular, the network is able to perform partial matching on symbolic information at high speed. As such, the system is aimed at the practical use of neural networks in high-speed reasoning systems. The paper describes the advantages and disadvantages of using CMM and shows how the approach overcomes those disadvantages. It then briefly describes a system incorporating CMM.",

keywords = "neural networks, associative memory, superimposed coding, rule-based systems",

author = "J Austin",

note = "Copyright {\textcopyright} 1996 Elsevier. This is an author produced version of a paper published in Fuzzy Sets and Systems.",

year = "1996",

month = sep,

day = "9",

doi = "10.1016/0165-0114(95)00258-8",

language = "English",

volume = "82",

pages = "223--233",

journal = "Fuzzy Sets and Systems",

issn = "0165-0114",

publisher = "Elsevier",

number = "2",

}

TY - JOUR

T1 - Distributed associative memories for high-speed symbolic reasoning

AU - Austin, J

PY - 1996/9/9

Y1 - 1996/9/9

N2 - This paper briefly introduces a novel symbolic reasoning system based upon distributed associative memories which are constructed from correlation matrix memories (CMM). The system is aimed at high-speed rule-based symbolic operations. It has the advantage of very fast rule matching without the long training times normally associated with neural-network-based symbolic manipulation systems. In particular, the network is able to perform partial matching on symbolic information at high speed. As such, the system is aimed at the practical use of neural networks in high-speed reasoning systems. The paper describes the advantages and disadvantages of using CMM and shows how the approach overcomes those disadvantages. It then briefly describes a system incorporating CMM.

AB - This paper briefly introduces a novel symbolic reasoning system based upon distributed associative memories which are constructed from correlation matrix memories (CMM). The system is aimed at high-speed rule-based symbolic operations. It has the advantage of very fast rule matching without the long training times normally associated with neural-network-based symbolic manipulation systems. In particular, the network is able to perform partial matching on symbolic information at high speed. As such, the system is aimed at the practical use of neural networks in high-speed reasoning systems. The paper describes the advantages and disadvantages of using CMM and shows how the approach overcomes those disadvantages. It then briefly describes a system incorporating CMM.

KW - neural networks

KW - associative memory

KW - superimposed coding

KW - rule-based systems

U2 - 10.1016/0165-0114(95)00258-8

DO - 10.1016/0165-0114(95)00258-8

M3 - Article

SN - 0165-0114

VL - 82

SP - 223

EP - 233

JO - Fuzzy Sets and Systems

JF - Fuzzy Sets and Systems

IS - 2

ER -