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

Details

Serval ID
serval:BIB_0CCC93AE4994
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Classification capacity of a modular neural network implementing neurally inspired architecture and training rules
Journal
IEEE Trans Neural Netw
Author(s)
Poirazi  P., Neocleous  C., Pattichis  C. S., Schizas  C. N.
ISSN
1045-9227 (Print)
Publication state
Published
Issued date
05/2004
Volume
15
Number
3
Pages
597-612
Notes
Journal Article
Research Support, Non-U.S. Gov't --- Old month value: May
Abstract
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.
Keywords
Animals Cerebral Cortex/anatomy & histology Humans *Models, Neurological *Neural Networks (Computer)
Pubmed
Web of science
Create date
28/01/2008 12:27
Last modification date
20/08/2019 12:34
Usage data