Skip to main content
Kent Academic Repository

Analysis of Saturation Problem in Ram-Based Neural Networks

Filho, E.C.D.B.C., Fairhurst, Michael, Bisset, D.L. (1992) Analysis of Saturation Problem in Ram-Based Neural Networks. Electronics Letters, 28 (4). pp. 345-347. ISSN 0013-5194. (doi:10.1049/el:19920216) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:22567)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided.
Official URL:
http://dx.doi.org/10.1049/el:19920216

Abstract

The problem of uneven saturation across the layers of RAM-based neural networks is investigated. It proposes a technique to generate a greater uniformity in saturation levels among the layers to specify the ideal connectivity between layers and to cope with the consequences of the saturation problem.

Item Type: Article
DOI/Identification number: 10.1049/el:19920216
Uncontrolled keywords: Neural Networks; Random-Access Memories
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Divisions > Division of Arts and Humanities > School of Arts
Depositing User: P. Ogbuji
Date Deposited: 05 Sep 2009 18:19 UTC
Last Modified: 05 Nov 2024 10:01 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/22567 (The current URI for this page, for reference purposes)

University of Kent Author Information

Fairhurst, Michael.

Creator's ORCID:
CReDIT Contributor Roles:
  • Depositors only (login required):

Total unique views for this document in KAR since July 2020. For more details click on the image.