Motivated Self-Organization - Archive ouverte HAL Access content directly
Conference Papers Year :

Motivated Self-Organization

(1) , (2)
1
2

Abstract

We present in this paper a variation of the self-organizing map algorithm where the original time-dependent (learning rate and neighborhood) learning function is replaced by a time-invariant one. The resulting self-organization does not fit the magnification law and the final vector density is not directly proportional to the density of the distribution. This lead us to introduce the notion of motivated self-organization where the self-organization is biased toward some data thanks to a supplementary signal. From a behavioral point of view, this signal may be understood as a motivational signal allowing a finer tuning of the final self-organization where needed. We illustrate this behavior through a simple robotic arm setup.
Fichier principal
Vignette du fichier
RougierBoniface-WSOM-2017.pdf (6.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01513519 , version 1 (25-04-2017)

Licence

Attribution - CC BY 4.0

Identifiers

  • HAL Id : hal-01513519 , version 1

Cite

Nicolas P. Rougier, Yann Boniface. Motivated Self-Organization. 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, , Jun 2017, Nancy, France. ⟨hal-01513519⟩
495 View
167 Download

Share

Gmail Facebook Twitter LinkedIn More