logo Idiap Research Institute        
 [BibTeX] [Marc21]
Two neural network construction methods
Type of publication: Journal paper
Citation: Thimm-97.5
Journal: Neural Processing Letters
Volume: 6
Number: 01
Year: 1997
Abstract: Two low complexity methods for neural network construction, that are applicable to various neural network models, are introduced and evaluated for high order perceptrons. The methods are based on a Boolean approximation of real-valued data. This approximation is used to construct an initial neural network topology which is subsequently trained on the original (real-valued) data. The methods are evaluated for their effectiveness in reducing the network size and increasing the network's generalization capabilities in comparison to fully connected high order perceptrons.
Userfields: ipdmembership={learning},
Keywords: Boolean logic, connectionism, high order neural network, high order perceptron, ontogenic neural network
Projects Idiap
Authors Thimm, Georg
Fiesler, Emile
Added by: [UNK]
Total mark: 0