Using event-based metric for event-based neural network weight adjustment

Bruno Cessac 1 Rodrigo Salas 2 Thierry Viéville 3, *
* Corresponding author
1 NEUROMATHCOMP - Mathematical and Computational Neuroscience
CRISAM - Inria Sophia Antipolis - Méditerranée , JAD - Laboratoire Jean Alexandre Dieudonné : UMR6621
3 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : The problem of adjusting the parameters of an event-based network model is addressed here at the programmatic level. Considering temporal processing, the goal is to adjust the network units weights so that the outcoming events correspond to what is desired. The present work proposes, in the deterministic and discrete case, a way to adapt usual alignment metrics in order to derive suitable adjustment rules. At the numerical level, the stability and unbiasness of the method is verified.
Document type :
Conference papers
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal.inria.fr/hal-00755345
Contributor : Thierry Viéville <>
Submitted on : Monday, December 3, 2012 - 11:32:54 AM
Last modification on : Thursday, May 3, 2018 - 1:32:58 PM
Long-term archiving on : Monday, March 4, 2013 - 2:40:09 AM

File

appendix.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00755345, version 1

Citation

Bruno Cessac, Rodrigo Salas, Thierry Viéville. Using event-based metric for event-based neural network weight adjustment. 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2012, Bruges, Belgium. 18 pp. ⟨hal-00755345⟩

Share

Metrics

Record views

599

Files downloads

187