Classification capacity of a modular neural network implementing neurally inspired architecture and training rules
Date
2004ISSN
1045-9227Source
IEEE Transactions on Neural NetworksVolume
15Issue
3Pages
597-612Google Scholar check
Keyword(s):
Metadata
Show full item recordAbstract
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.
Collections
Cite as
Related items
Showing items related by title, author, creator and subject.
-
Article
Erratum: Dynamical neural networks that ensure exponential identification error convergence (Neural Networks (1997) 10:2 (299-314)) PII S0893608098000409
Kosmatopoulos, E. B.; Christodoulou, Manolis A.; Ioannou, Petros A. (1998)
-
Conference Object
Dynamic Autoregressive Neural Networks for Spatially Distributed Time Series Prediction of Car Crashes in Urban Networks
Dimitriou, Loukas; Hassan, Hany (2013)
-
Conference Object
A generic reconfigurable neural network architecture implemented as a network on chip
Theocharides, Theocharis; Link, G.; Vijaykrishnan, N.; Irwin, M. J.; Srikantam, V. (2004)