REPLICA SYMMETRY BREAKING IN NEURAL NETWORKS WITH NON-MONOTONE ACTIVATION FUNCTION

A. Lamura, C. Marangi () and G. Nardulli ()
Additional contact information
A. Lamura: Dipartimento di Fisica, dell'Universita' di Bari, 70100 Bari, Italy
C. Marangi: Istituto Nazionale di Fisica Nucleare and Istituto per Ricerche di Matematica Applicata, CNR, 70100 Bari, Italy
G. Nardulli: Dipartimento di Fisica, dell'Universita' di Bari and Istituto Nazionale di Fisica Nucleare, 70100 Bari, Italy

International Journal of Modern Physics C (IJMPC), 1996, vol. 07, issue 01, 19-32

Abstract: In this paper we analyze replica symmetry breaking in attractor neural networks with non-monotone activation function. We study the non-monotone version of the Edinburgh model, which allows the control of the domains of attraction by the stability parameterK, and we compute, at one step of symmetry breaking, storage capacity and, for the strongly dilute model, the domains of attraction of the stable fixed points.

Keywords: Attractor Neural Networks; Replica Method (search for similar items in EconPapers)
Date: 1996
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S012918319600003X
Access to full text is restricted to subscribers

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:wsi:ijmpcx:v:07:y:1996:i:01:n:s012918319600003x

Ordering information: This journal article can be ordered from

DOI: 10.1142/S012918319600003X

Access Statistics for this article

International Journal of Modern Physics C (IJMPC) is currently edited by H. J. Herrmann

More articles in International Journal of Modern Physics C (IJMPC) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().