Star-CNN is a particular architecture of Cellular Neural Networks that has been recently proposed. This dynamic nonlinear system is defined by connecting N identical dynamical sysstem called local cell with a Central System in the shape of a star. Each of the local cells communicates with others through the Central System. Because of the hardware requirements of such a system, its implementation comes out extremely expansive from the silicon area occupation point of view. This paper presents a hardwaare implementation of this new CNN architecture based on a time division approach that allows to significantly reduce the silicon area occupation by minimizing the number of the analogue multipliers. © 2008 IEEE.
Sargeni, F., Bonaiuto, V., & Bonifazi, M. (2006). Multiplexed circuit for star-CNN architecture. In Proceedings of the 2006 10th IEEE international workshop on cellular neural networks and their applications (pp.191-195). New York : IEEE.
Autori: | |
Autori: | Sargeni, F; Bonaiuto, V; Bonifazi, M |
Titolo: | Multiplexed circuit for star-CNN architecture |
Nome del convegno: | 2006 10th IEEE international workshop on cellular neural networks and their applications, CNNA 2006 |
Luogo del convegno: | Istanbul |
Anno del convegno: | 2006 |
Enti collegati al convegno: | Scientific and Technological Research Council of Turkey (TUBITAK);SIEMENS San. ve Tic. A.S.;Office of Naval Research (ONR);IEEE CAS Society |
Rilevanza: | Rilevanza internazionale |
Sezione: | contributo |
Data di pubblicazione: | 2006 |
Digital Object Identifier (DOI): | http://dx.doi.org/10.1109/CNNA.2006.341628 |
Settore Scientifico Disciplinare: | Settore ING-IND/31 - Elettrotecnica |
Lingua: | English |
Tipologia: | Intervento a convegno |
Citazione: | Sargeni, F., Bonaiuto, V., & Bonifazi, M. (2006). Multiplexed circuit for star-CNN architecture. In Proceedings of the 2006 10th IEEE international workshop on cellular neural networks and their applications (pp.191-195). New York : IEEE. |
Appare nelle tipologie: | 02 - Intervento a convegno |