Data fusion using dynamic associative memory

Titus K. Lo; Henry Leung; Chun Chung Chan

Data fusion using dynamic associative memory

Titus K. Lo, Henry Leung, Chun Chung Chan

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

2 Citations (Scopus)

Abstract

An associative memory, unlike an addressed memory used in conventional computers, is content addressable. That is, storing and retrieving information are not based on the location of the memory cell but on the content of the information. There are a number of approaches to implement an associative memory, one of which is to use a neural dynamical system where objects being memorized or recognized correspond to its basic attractors. The work presented in this paper is the investigation of applying a particular type of neural dynamical associative memory, namely the projection network, to pattern recognition and data fusion. Three types of attractors, which are fixed-point, limit- cycle, and chaotic, have been studied, evaluated and compared.

Original language	English
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Publisher	Society of Photo-Optical Instrumentation Engineers
Pages	354-365
Number of pages	12
Volume	3068
ISBN (Print)	0819424838
Publication status	Published - 1 Dec 1997
Externally published	Yes
Event	Signal Processing, Sensor Fusion, and Target Recognition VI - Orlando, FL, United States Duration: 21 Apr 1997 → 24 Apr 1997

Conference

Conference	Signal Processing, Sensor Fusion, and Target Recognition VI
Country/Territory	United States
City	Orlando, FL
Period	21/04/97 → 24/04/97

ASJC Scopus subject areas

Electrical and Electronic Engineering
Condensed Matter Physics

Cite this

@inproceedings{122870811fa6430bb85b069835e7f1e6,

title = "Data fusion using dynamic associative memory",

abstract = "An associative memory, unlike an addressed memory used in conventional computers, is content addressable. That is, storing and retrieving information are not based on the location of the memory cell but on the content of the information. There are a number of approaches to implement an associative memory, one of which is to use a neural dynamical system where objects being memorized or recognized correspond to its basic attractors. The work presented in this paper is the investigation of applying a particular type of neural dynamical associative memory, namely the projection network, to pattern recognition and data fusion. Three types of attractors, which are fixed-point, limit- cycle, and chaotic, have been studied, evaluated and compared.",

author = "Lo, {Titus K.} and Henry Leung and Chan, {Chun Chung}",

year = "1997",

month = dec,

day = "1",

language = "English",

isbn = "0819424838",

volume = "3068",

pages = "354--365",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "Society of Photo-Optical Instrumentation Engineers",

note = "Signal Processing, Sensor Fusion, and Target Recognition VI ; Conference date: 21-04-1997 Through 24-04-1997",

}

Data fusion using dynamic associative memory. / Lo, Titus K.; Leung, Henry; Chan, Chun Chung.
Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3068 Society of Photo-Optical Instrumentation Engineers, 1997. p. 354-365.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Data fusion using dynamic associative memory

AU - Lo, Titus K.

AU - Leung, Henry

AU - Chan, Chun Chung

PY - 1997/12/1

Y1 - 1997/12/1

N2 - An associative memory, unlike an addressed memory used in conventional computers, is content addressable. That is, storing and retrieving information are not based on the location of the memory cell but on the content of the information. There are a number of approaches to implement an associative memory, one of which is to use a neural dynamical system where objects being memorized or recognized correspond to its basic attractors. The work presented in this paper is the investigation of applying a particular type of neural dynamical associative memory, namely the projection network, to pattern recognition and data fusion. Three types of attractors, which are fixed-point, limit- cycle, and chaotic, have been studied, evaluated and compared.

AB - An associative memory, unlike an addressed memory used in conventional computers, is content addressable. That is, storing and retrieving information are not based on the location of the memory cell but on the content of the information. There are a number of approaches to implement an associative memory, one of which is to use a neural dynamical system where objects being memorized or recognized correspond to its basic attractors. The work presented in this paper is the investigation of applying a particular type of neural dynamical associative memory, namely the projection network, to pattern recognition and data fusion. Three types of attractors, which are fixed-point, limit- cycle, and chaotic, have been studied, evaluated and compared.

UR - http://www.scopus.com/inward/record.url?scp=0031342194&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SN - 0819424838

VL - 3068

SP - 354

EP - 365

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Society of Photo-Optical Instrumentation Engineers

T2 - Signal Processing, Sensor Fusion, and Target Recognition VI

Y2 - 21 April 1997 through 24 April 1997

ER -

Data fusion using dynamic associative memory

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this