Method of Parallel-Hierarchical Network Self-Training and its Application for Pattern Classification and Recognition

Propositions necessary for development of parallel-hierarchical (PH) network training methods are discussed in this article. Unlike already known structures of the artificial neural network, where non-normalized (absolute) similarity criteria are used for comparison, the suggested structure uses a...

Description complète

Détails bibliographiques

Auteurs principaux:	TIMCHENKO, L., KOKRIATSKAIA, N., MELNIKOV, V., MAKARENKO, R., PETROVSKYI, N.
Format:	Artigo
Langue:	Inglês
Publié:	Stefan cel Mare University of Suceava 2012-11-01
Collection:	Advances in Electrical and Computer Engineering
Sujets:	parallel-hierarchical network training population coding preparation face recognition
Accès en ligne:	http://dx.doi.org/10.4316/AECE.2012.04006
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!