Correctness of the FPNA neural paradigm - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports Year : 2000

Correctness of the FPNA neural paradigm

Bernard Girau


Neural networks are usually considered as naturally parallel computing models. But the number of operators and the complex connection graphs of standard neural models can not be handled by digital hardware devices. A new theoretical and practical framework allows to reconcile simple hardware topologies with complex neural architectures: Field Programmable Neural Arrays (FPNA) lead to powerful neural architectures that are easy to map onto digital hardware, thanks to a simplified topology and an original data exchange scheme. This report describes the basic principles of the FPNA paradigm. Formal definitions are introduced and illustrated. Two computation methods for feedforward FPNAs are introduced. The proof of their correctness is sketched.
Fichier principal
Vignette du fichier
A00-R-023.pdf (185.63 Ko) Télécharger le fichier

Dates and versions

inria-00099071 , version 1 (26-09-2006)


  • HAL Id : inria-00099071 , version 1


Bernard Girau. Correctness of the FPNA neural paradigm. [Intern report] A00-R-023 || girau00o, 2000, 8 p. ⟨inria-00099071⟩
153 View
38 Download


Gmail Facebook Twitter LinkedIn More