Cellular Self-Organising Maps - CSOM

Bernard Girau (1) , Andres Upegui (2)

1 BISCUIT - Bio-Inspired, Situated and Cellular Unconventional Information Technologies
2 HEPIA - Haute Ecole du Paysage, d'Ingénierie et d'Architecture de Genève

This paper presents CSOM, a Cellular Self-Organising Map which performs weight update in a cellular manner. Instead of updating weights towards new input vectors, it uses a signal propagation originated from the best matching unit to every other neuron in the network. Interactions between neurons are thus local and distributed. In this paper we present performance results showing than CSOM can obtain faster and better quantisation than classical SOM when used on high-dimensional vectors. We also present an application on video compression based on vector quantisation, in which CSOM outperforms SOM.

Mots clés: neural networks; self-organising maps; cellular computing

Domaines: Réseau de neurones [cs.NE]

Bernard Girau, Andres Upegui. Cellular Self-Organising Maps - CSOM. WSOM'19 - 13th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization, Jun 2019, Barcelona, Spain. ⟨10.1007/978-3-030-19642-4_4⟩. ⟨hal-02156280⟩