Classification capacity of a modular neural network implementing neurally inspired architecture and training rules

Détails

ID Serval
serval:BIB_0CCC93AE4994
Type
Article: article d'un périodique ou d'un magazine.
Collection
Publications
Titre
Classification capacity of a modular neural network implementing neurally inspired architecture and training rules
Périodique
IEEE Trans Neural Netw
Auteur(s)
Poirazi  P., Neocleous  C., Pattichis  C. S., Schizas  C. N.
ISSN
1045-9227 (Print)
Statut éditorial
Publié
Date de publication
05/2004
Volume
15
Numéro
3
Pages
597-612
Notes
Journal Article
Research Support, Non-U.S. Gov't --- Old month value: May
Résumé
A three-layer neural network (NN) with novel adaptive architecture has been developed. The hidden layer of the network consists of slabs of single neuron models, where neurons within a slab--but not between slabs--have the same type of activation function. The network activation functions in all three layers have adaptable parameters. The network was trained using a biologically inspired, guided-annealing learning rule on a variety of medical data. Good training/testing classification performance was obtained on all data sets tested. The performance achieved was comparable to that of SVM classifiers. It was shown that the adaptive network architecture, inspired from the modular organization often encountered in the mammalian cerebral cortex, can benefit classification performance.
Mots-clé
Animals Cerebral Cortex/anatomy & histology Humans *Models, Neurological *Neural Networks (Computer)
Pubmed
Web of science
Création de la notice
28/01/2008 13:27
Dernière modification de la notice
03/03/2018 13:38
Données d'usage