Skip to Main content Skip to Navigation
Book sections

Consensus Driven Self-Organization: Towards Non Hierarchical Multi-Map Architectures

Noémie Gonnier 1, 2 Yann Boniface 2 Hervé Frezza-Buet 1, 2
1 CentraleSupélec
2 BISCUIT - Bio-Inspired, Situated and Cellular Unconventional Information Technologies
LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : This paper introduces CxSOM, a model to build modular architectures based on self-organizing maps (SOM). An original consensus driven approach enables to adress non-hierarchical architectures where SOMs get organized jointly. The paper aims at showing how the modules are able to store the association between data, and evaluating, by a mutual information criterion, the resulting organization. These results stand as preliminary work to study bigger architectures.
Keywords : Neural Network Models Self-Organizing Maps Multi-Modal Architecture
Document type :
Book sections
Complete list of metadatas
https://hal-centralesupelec.archives-ouvertes.fr/hal-03030518
Contributor : Noémie Gonnier <>
Submitted on : Monday, November 30, 2020 - 10:23:02 AM
Last modification on : Wednesday, December 2, 2020 - 3:37:47 AM

File

Vignette du document
sub_491.pdf
Files produced by the author(s)

Identifiers

Collections

CENTRALESUPELEC | UNIV-LORRAINE | LORIA | CNRS | INRIA | LORIA-AIS

Citation

Noémie Gonnier, Yann Boniface, Hervé Frezza-Buet. Consensus Driven Self-Organization: Towards Non Hierarchical Multi-Map Architectures. Communications in Computer and Information Science, Neural Information Processing, ICONIP 2020, pp.526-534, 2020, ⟨10.1007/978-3-030-63823-8_60⟩. ⟨hal-03030518⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

29

Files downloads

48