Fiber bundles and receptive neural fields

Abstract : Some networks, like RBF networks or Kohonen feature maps, can be viewed as mappings from an input manifold (the signal space) to a neural receptive field, generally lower dimensional. The activation of a neuron, given by application of a smooth function to a weighted norm of the difference between the input and the so called center of the cell, can be thought as a membership value to a one point set. Generalizing this approach leads to the concept of halo around a set. The base set and its halo constitute a topological pair and can be provided with a membership function. The resulting triples are then used as total and base space for a fibered structure that provides a general framework for dealing with neural fields.
Type de document :
Communication dans un congrès
ICNN 1997, International Conference on Neural Networks, Jun 1997, Houston, United States. IEEE, pp 1127-1130, 1997, 〈10.1109/ICNN.1997.616188〉
Liste complète des métadonnées

https://hal-enac.archives-ouvertes.fr/hal-01020966
Contributeur : Céline Smith <>
Soumis le : mardi 8 juillet 2014 - 17:37:20
Dernière modification le : mardi 30 janvier 2018 - 13:52:01

Identifiants

Collections

Citation

Stéphane Puechmorel. Fiber bundles and receptive neural fields. ICNN 1997, International Conference on Neural Networks, Jun 1997, Houston, United States. IEEE, pp 1127-1130, 1997, 〈10.1109/ICNN.1997.616188〉. 〈hal-01020966〉

Partager

Métriques

Consultations de la notice

94