Analogy between Markov chain and the asynchronous memory recall process of Hebbian-type associative memory

Chun ying Ho, Iwao Sasase, Shinsaku Mori

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Analytical techniques related to the Markov chain are utilized to study the capacity and recall probability of Hebbian-type associative memory (HAM). The concept is based on the analogy between the Markov chain and the asynchronous iterative memory recall process of HAM. Calculation of the limiting zero state probability of a birth-death process of incorrect bits of the probe leads to a faithful estimation of the recall probability for a given HAM. Results obtained show a strong resemblance to those obtained by J. J. Hopfield (1982). However, time-consuming computational simulation requirements can be avoided by the proposed method. Moreover, it has been shown that the recall probability of a given HAM is independent of the initial Hamming distance between the probe and the nearest memory state as the number of asynchronous recall iterations tends to infinity.

Original languageEnglish
Title of host publication1991 IEEE International Joint Conference on Neural Networks
PublisherPubl by IEEE
Pages13-18
Number of pages6
ISBN (Print)0780302273
Publication statusPublished - 1992
Externally publishedYes
Event1991 IEEE International Joint Conference on Neural Networks - IJCNN '91 - Singapore, Singapore
Duration: 1991 Nov 181991 Nov 21

Other

Other1991 IEEE International Joint Conference on Neural Networks - IJCNN '91
CitySingapore, Singapore
Period91/11/1891/11/21

Fingerprint

Markov processes
Data storage equipment
Hamming distance

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ho, C. Y., Sasase, I., & Mori, S. (1992). Analogy between Markov chain and the asynchronous memory recall process of Hebbian-type associative memory. In 1991 IEEE International Joint Conference on Neural Networks (pp. 13-18). Publ by IEEE.

Analogy between Markov chain and the asynchronous memory recall process of Hebbian-type associative memory. / Ho, Chun ying; Sasase, Iwao; Mori, Shinsaku.

1991 IEEE International Joint Conference on Neural Networks. Publ by IEEE, 1992. p. 13-18.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ho, CY, Sasase, I & Mori, S 1992, Analogy between Markov chain and the asynchronous memory recall process of Hebbian-type associative memory. in 1991 IEEE International Joint Conference on Neural Networks. Publ by IEEE, pp. 13-18, 1991 IEEE International Joint Conference on Neural Networks - IJCNN '91, Singapore, Singapore, 91/11/18.
Ho CY, Sasase I, Mori S. Analogy between Markov chain and the asynchronous memory recall process of Hebbian-type associative memory. In 1991 IEEE International Joint Conference on Neural Networks. Publ by IEEE. 1992. p. 13-18
Ho, Chun ying ; Sasase, Iwao ; Mori, Shinsaku. / Analogy between Markov chain and the asynchronous memory recall process of Hebbian-type associative memory. 1991 IEEE International Joint Conference on Neural Networks. Publ by IEEE, 1992. pp. 13-18
@inproceedings{d12870d756bf4ff2bf271c874f2afee5,
title = "Analogy between Markov chain and the asynchronous memory recall process of Hebbian-type associative memory",
abstract = "Analytical techniques related to the Markov chain are utilized to study the capacity and recall probability of Hebbian-type associative memory (HAM). The concept is based on the analogy between the Markov chain and the asynchronous iterative memory recall process of HAM. Calculation of the limiting zero state probability of a birth-death process of incorrect bits of the probe leads to a faithful estimation of the recall probability for a given HAM. Results obtained show a strong resemblance to those obtained by J. J. Hopfield (1982). However, time-consuming computational simulation requirements can be avoided by the proposed method. Moreover, it has been shown that the recall probability of a given HAM is independent of the initial Hamming distance between the probe and the nearest memory state as the number of asynchronous recall iterations tends to infinity.",
author = "Ho, {Chun ying} and Iwao Sasase and Shinsaku Mori",
year = "1992",
language = "English",
isbn = "0780302273",
pages = "13--18",
booktitle = "1991 IEEE International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Analogy between Markov chain and the asynchronous memory recall process of Hebbian-type associative memory

AU - Ho, Chun ying

AU - Sasase, Iwao

AU - Mori, Shinsaku

PY - 1992

Y1 - 1992

N2 - Analytical techniques related to the Markov chain are utilized to study the capacity and recall probability of Hebbian-type associative memory (HAM). The concept is based on the analogy between the Markov chain and the asynchronous iterative memory recall process of HAM. Calculation of the limiting zero state probability of a birth-death process of incorrect bits of the probe leads to a faithful estimation of the recall probability for a given HAM. Results obtained show a strong resemblance to those obtained by J. J. Hopfield (1982). However, time-consuming computational simulation requirements can be avoided by the proposed method. Moreover, it has been shown that the recall probability of a given HAM is independent of the initial Hamming distance between the probe and the nearest memory state as the number of asynchronous recall iterations tends to infinity.

AB - Analytical techniques related to the Markov chain are utilized to study the capacity and recall probability of Hebbian-type associative memory (HAM). The concept is based on the analogy between the Markov chain and the asynchronous iterative memory recall process of HAM. Calculation of the limiting zero state probability of a birth-death process of incorrect bits of the probe leads to a faithful estimation of the recall probability for a given HAM. Results obtained show a strong resemblance to those obtained by J. J. Hopfield (1982). However, time-consuming computational simulation requirements can be avoided by the proposed method. Moreover, it has been shown that the recall probability of a given HAM is independent of the initial Hamming distance between the probe and the nearest memory state as the number of asynchronous recall iterations tends to infinity.

UR - http://www.scopus.com/inward/record.url?scp=0027094365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027094365&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780302273

SP - 13

EP - 18

BT - 1991 IEEE International Joint Conference on Neural Networks

PB - Publ by IEEE

ER -