Skip to Main content Skip to Navigation
Reports

FPNA, FPNN: from programmable fields to topologically simplified neural networks

Bernard Girau 1
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This work aims at developping neural architectures that are easy to map onto FPGAs, thanks to a simplified topology and an original data exchange scheme, without having any loss of approximation capability. Thie report proposes a brief overview of FPNA and FPNN definitions, computations and implementations.
Document type :
Reports
Complete list of metadata

https://hal.inria.fr/inria-00107829
Contributor : Publications Loria <>
Submitted on : Thursday, October 19, 2006 - 9:11:11 AM
Last modification on : Friday, February 26, 2021 - 3:28:03 PM
Long-term archiving on: : Friday, November 25, 2016 - 12:51:54 PM

Identifiers

  • HAL Id : inria-00107829, version 1

Collections

Citation

Bernard Girau. FPNA, FPNN: from programmable fields to topologically simplified neural networks. [Intern report] 99-R-019 || girau99w, 1999, 12 p. ⟨inria-00107829⟩

Share

Metrics

Record views

253

Files downloads

145