On rates of convergence for the overlap in the Hopfield model
- We consider the Hopfield model with n neurons and an increasing number p=p(n) of randomly chosen patterns and use Stein's method to obtain rates of convergence for the central limit theorem of overlap parameters, which holds for every fixed choice of the overlap parameter for almost all realisations of the random patterns.
Document Type: | Article |
---|---|
Language: | English |
Author: | Peter Eichelsbacher, Bastian Martschink |
Parent Title (German): | Münster Journal of Mathematics |
Volume: | 7 |
Issue: | 2 |
First Page: | 731 |
Last Page: | 752 |
ISSN: | 1867-5778 |
DOI: | https://doi.org/10.17879/58269754868 |
ArXiv Id: | http://arxiv.org/abs/1303.5252 |
Date of first publication: | 2013/03/21 |
Departments, institutes and facilities: | Fachbereich Ingenieurwissenschaften und Kommunikation |
Dewey Decimal Classification (DDC): | 5 Naturwissenschaften und Mathematik / 51 Mathematik / 519 Wahrscheinlichkeiten, angewandte Mathematik |
Entry in this database: | 2015/04/02 |