Finite temperature study of retrieval time in Hopfield network

M. Ghosh

Physica A: Statistical Mechanics and its Applications, 1992, vol. 181, issue 1, 23-28

Abstract: A numerical study of retrieval time τ of a distorted pattern to a learned one is reported here for finite temperatures. For a fixed memory loading capacity α (below the network's zero temperature critical loading capacity; αc), no retrieval solution appears above a temperature TM(α). We have found numerically the values of TM (the point beyond which the overlap with the learned pattern disappears) and the time required for the recall of a distorted pattern (with fixed but small distortion) as one approaches the TM(α) phase boundary, using a finite temperature Monte Carlo simulation for a system with 500 spins.

Date: 1992
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/037843719290194U
Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:phsmap:v:181:y:1992:i:1:p:23-28

DOI: 10.1016/0378-4371(92)90194-U

Access Statistics for this article

Physica A: Statistical Mechanics and its Applications is currently edited by K. A. Dawson, J. O. Indekeu, H.E. Stanley and C. Tsallis

More articles in Physica A: Statistical Mechanics and its Applications from Elsevier
Bibliographic data for series maintained by Catherine Liu ().