A modified Self Organizing Map for semantic impairment - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2024

A modified Self Organizing Map for semantic impairment


In 1982 Teuvo Kohonen proposed an algorithm called Self Organizing Map (SOM) that is basically a stochastic model of the establishment of topology preserving connections between the retina and the cortex in our brain. That model has proved an efficient classification tool, a source of inspiration for other biological models and also for the understanding of the principles of self-organization. In this paper, we present a modification of the initial SOM to address an important problem in semantic cognition: the representation of human concepts in the brain. Much of the knowledge acquired in the last decades in this field comes from the study of patients with acquired difficulties in language. The modification presented here is inspired in semantic dementia, a devastating pathology that introduces the deterioration of semantic knowledge into the brain. The paper discusses the model and describes some preliminary results that show its interest as the basis of possible new tools to help to understand the considered type of diseases.
Fichier principal
Vignette du fichier
paperMITA.pdf (535.89 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04358017 , version 1 (21-12-2023)


Public Domain


  • HAL Id : hal-04358017 , version 1


Sebastián Basterrech, Jorge Graneri, Eduardo Mizraji, Gerardo Rubino. A modified Self Organizing Map for semantic impairment. MITA 2023 - 19th International Conference on Multimedia Information Technology and Applications, Technical University of Ostrava, Czechia, Jul 2023, Ostrava, Czech Republic. pp.1-9. ⟨hal-04358017⟩
37 View
6 Download


Gmail Facebook X LinkedIn More