DYNAMICAL PROPERTIES OF NEURAL NETWORKS WITH CORRELATED PATTERNS

C. Marangi, G. Nardulli and G. Pasquariello
Additional contact information
C. Marangi: Dipartimento di Fisica dell’Università di Bari, Istituto Nazionale Fisica Nucleare, Sezione di Bari, Via Amendola 173, 70126 Bari, Italy
G. Nardulli: Dipartimento di Fisica dell’Università di Bari, Istituto Nazionale Fisica Nucleare, Sezione di Bari, Via Amendola 173, 70126 Bari, Italy
G. Pasquariello: Istituto Elaborazione Segnali e Immagini—C.N.R., Via Amendola 173, 70126 Bari, Italy

International Journal of Modern Physics C (IJMPC), 1991, vol. 02, issue 03, 773-786

Abstract: We investigate the retrieval properties of fully connected saturated neural networks trained by the Edinburgh algorithm with correlated patterns{ξi}. We evaluate the effect of the correlation on the overlap between{ξi}and the network configuration after one time step and on the basins of attraction. We also show that the introduction of the thermal noise does not change the domains of attraction of the correlated memories.

Keywords: Attractor Neural Networks; Domains of Attraction; Correlated Patterns (search for similar items in EconPapers)
Date: 1991
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0129183191000998
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:02:y:1991:i:03:n:s0129183191000998

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0129183191000998

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 ().