Massively distributed implementation of a spiking neural network for image segmentation on FPGA

Bernard Girau 1 Cesar Torres-Huitzil 2
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Numerous neural network hardware implementations now use digital reconfigurable devices such as Field Programmable Gate Arrays (FPGAs) thanks to an interesting compromise between the hardware efficiency of Application Specific Integrated Circuits (ASICs) and the flexibility of a simple software-like handling. Another current trend of neural research focuses on elementary neural mechanisms such as spiking neurons. Their rather simple and asynchronous behavior have motivated several implementations on analog devices, whereas digital implementations appear as quite unable to handle large spiking neural networks, for lack of density. In this paper, we develop an optimized FPGA implementation of a standard spiking model (LEGION) of integrate-and-fire neurons, used for sequence image segmentation. Despite previous research, little progress has been made in building successful neural systems for image segmentation in digital hardware. This work shows that digital and flexible solutions may efficiently handle large networks of spiking neurons.
Type de document :
Article dans une revue
Neural Information Processing - Letters and Reviews, KAIST Press, 2006, 10 (4-6), pp.105-114
Liste complète des métadonnées

https://hal.inria.fr/inria-00256355
Contributeur : Bernard Girau <>
Soumis le : vendredi 15 février 2008 - 12:05:29
Dernière modification le : jeudi 11 janvier 2018 - 06:19:48

Identifiants

  • HAL Id : inria-00256355, version 1

Collections

Citation

Bernard Girau, Cesar Torres-Huitzil. Massively distributed implementation of a spiking neural network for image segmentation on FPGA. Neural Information Processing - Letters and Reviews, KAIST Press, 2006, 10 (4-6), pp.105-114. 〈inria-00256355〉

Partager

Métriques

Consultations de la notice

245