Skip to Main content Skip to Navigation
New interface
Reports (Research report)

A deterministic biologically plausible classifier

Thierry Viéville 1 Sylvie Crahay 1 
1 ODYSSEE - Computer and biological vision
DI-ENS - Département d'informatique - ENS Paris, CRISAM - Inria Sophia Antipolis - Méditerranée , ENS-PSL - École normale supérieure - Paris, Inria Paris-Rocquencourt, ENPC - École des Ponts ParisTech
Abstract : Considering the «data classification» problem it is known that efficient classifiers only consider a few (pertinent) parameters. This seems in contradiction with usual biological plausible models, based on neuronal networks, which intrinsically have a lot of parameters. Here, we propose to solve this apparent contradiction, building a link between biological plausible models and classifiers with low Vapnik-Chernovenkis dimension. The -somehow very simple- key idea is to consider piece-wise linear classifiers of minimal dimension, as a generalization of support-vector machine. This allows to solve the previous dilemma at both a theoretical and computational levels, including some elements of biological plausibility. Experimentation of a small interactive toy demonstration to analyze the performances of these mechanisms is reported, while the methodology is validated on a real experimental problems.
Document type :
Reports (Research report)
Complete list of metadata

Cited literature [1 references]  Display  Hide  Download
Contributor : Rapport De Recherche Inria Connect in order to contact the contributor
Submitted on : Tuesday, May 23, 2006 - 7:47:20 PM
Last modification on : Wednesday, October 26, 2022 - 8:16:49 AM
Long-term archiving on: : Sunday, April 4, 2010 - 10:53:08 PM


  • HAL Id : inria-00072099, version 1



Thierry Viéville, Sylvie Crahay. A deterministic biologically plausible classifier. [Research Report] RR-4489, INRIA. 2002. ⟨inria-00072099⟩



Record views


Files downloads