MEAN FIELD MONTE CARLO STUDIES OF ASSOCIATIVE MEMORY - Understanding the Dynamics of a Many-pattern Model

Ish Dhand, Manoranjan P. Singh

2011

Abstract

Dynamics of a Hebbian model of associative memory is studied using Mean field Monte-Carlo method. Under the assumption of infinite system, we have derived single-spin equations, using the generating functional method from statistical mechanics, for the purpose of simulations. This approach circumvents the strong finite-size effects of the usual calculations on this system. We have tried to understand the retrieval of a stored pattern in presence of another condensed pattern undergoing reinforcement, positive or negative. We find that the retrieval is faster and the retrieval quality is better for the case of positive reinforcement.

Paper Citation

in Harvard Style

Dhand I. and P. Singh M. (2011). MEAN FIELD MONTE CARLO STUDIES OF ASSOCIATIVE MEMORY - Understanding the Dynamics of a Many-pattern Model . In Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011) ISBN 978-989-8425-84-3, pages 395-400. DOI: 10.5220/0003683803950400

in Bibtex Style

@conference{ncta11,
author={Ish Dhand and Manoranjan P. Singh},
title={MEAN FIELD MONTE CARLO STUDIES OF ASSOCIATIVE MEMORY - Understanding the Dynamics of a Many-pattern Model},
booktitle={Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011)},
year={2011},
pages={395-400},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003683803950400},
isbn={978-989-8425-84-3},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011)
TI - MEAN FIELD MONTE CARLO STUDIES OF ASSOCIATIVE MEMORY - Understanding the Dynamics of a Many-pattern Model
SN - 978-989-8425-84-3
AU - Dhand I.
AU - P. Singh M.
PY - 2011
SP - 395
EP - 400
DO - 10.5220/0003683803950400