Towards a high capacity fuzzy associative memory model

Fu Lai Korris Chung; Tong Lee

Towards a high capacity fuzzy associative memory model

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

7 Citations (Scopus)

Abstract

Kosko's fuzzy associative memory (FAM) is the very first example to use neural networks to articulate fuzzy rules for fuzzy systems. Despite its simplicity and modularity, the model suffers from extremely low memory capacity, i.e., single rule pattern storage, and hence it is limited to small rule-base applications. In this paper, a high capacity FAM model called fuzzy relational memory (FRM) is proposed. Based upon the well-developed theoretical results of solving fuzzy relational equations, a theorem for perfect recalls of all stored rules is established and two effective encoding algorithms namely orthogonal encoding and weighted encoding are devised. The performance of the new model is reported and compared with that of the FAM model through numerous examples.

Original language	English
Title of host publication	IEEE International Conference on Neural Networks - Conference Proceedings
Publisher	IEEE
Pages	1595-1599
Number of pages	5
Publication status	Published - 1 Dec 1994
Externally published	Yes
Event	Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, United States Duration: 27 Jun 1994 → 29 Jun 1994

Conference

Conference	Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
Country/Territory	United States
City	Orlando, FL
Period	27/06/94 → 29/06/94

ASJC Scopus subject areas

Software

Cite this

@inproceedings{8793a5e9abbf442e9a7cc288fd5b3f90,

title = "Towards a high capacity fuzzy associative memory model",

abstract = "Kosko's fuzzy associative memory (FAM) is the very first example to use neural networks to articulate fuzzy rules for fuzzy systems. Despite its simplicity and modularity, the model suffers from extremely low memory capacity, i.e., single rule pattern storage, and hence it is limited to small rule-base applications. In this paper, a high capacity FAM model called fuzzy relational memory (FRM) is proposed. Based upon the well-developed theoretical results of solving fuzzy relational equations, a theorem for perfect recalls of all stored rules is established and two effective encoding algorithms namely orthogonal encoding and weighted encoding are devised. The performance of the new model is reported and compared with that of the FAM model through numerous examples.",

author = "Chung, {Fu Lai Korris} and Tong Lee",

year = "1994",

month = dec,

day = "1",

language = "English",

pages = "1595--1599",

booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

publisher = "IEEE",

address = "United States",

note = "Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) ; Conference date: 27-06-1994 Through 29-06-1994",

}

TY - GEN

T1 - Towards a high capacity fuzzy associative memory model

AU - Chung, Fu Lai Korris

AU - Lee, Tong

PY - 1994/12/1

Y1 - 1994/12/1

N2 - Kosko's fuzzy associative memory (FAM) is the very first example to use neural networks to articulate fuzzy rules for fuzzy systems. Despite its simplicity and modularity, the model suffers from extremely low memory capacity, i.e., single rule pattern storage, and hence it is limited to small rule-base applications. In this paper, a high capacity FAM model called fuzzy relational memory (FRM) is proposed. Based upon the well-developed theoretical results of solving fuzzy relational equations, a theorem for perfect recalls of all stored rules is established and two effective encoding algorithms namely orthogonal encoding and weighted encoding are devised. The performance of the new model is reported and compared with that of the FAM model through numerous examples.

AB - Kosko's fuzzy associative memory (FAM) is the very first example to use neural networks to articulate fuzzy rules for fuzzy systems. Despite its simplicity and modularity, the model suffers from extremely low memory capacity, i.e., single rule pattern storage, and hence it is limited to small rule-base applications. In this paper, a high capacity FAM model called fuzzy relational memory (FRM) is proposed. Based upon the well-developed theoretical results of solving fuzzy relational equations, a theorem for perfect recalls of all stored rules is established and two effective encoding algorithms namely orthogonal encoding and weighted encoding are devised. The performance of the new model is reported and compared with that of the FAM model through numerous examples.

UR - http://www.scopus.com/inward/record.url?scp=0028750165&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SP - 1595

EP - 1599

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

T2 - Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)

Y2 - 27 June 1994 through 29 June 1994

ER -

Towards a high capacity fuzzy associative memory model

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this