Abstract
Two different approaches in constructing Neural Network (NN) classifiers are discussed — discriminant-based networks and Region of Influence networks. A general model for ROI networks is presented, and the different functionalities of this structure are discussed: classification, vector quantization and associative memory.
Also, an architecture for this model's implementation is presented, and the hardware realization of each layer is reviewed in detail.
co-author J.M.Moreno is an FI scholar under the Generalitat de Catalunya's Education Dept.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Bibliography
Reilly D.L., Cooper L.N., Elbaum C. A neural model for category learning. Biological Cybernetics, 45, 35–41 1982
Alpaydin A.I. Neural models of incremental supervised and unsupervised learning. PhD Thesis Lausanne EPFL 1990
Castillo F. Digital VLSI Architectures for Neural Networks. PhD Thesis Universidad Politécnica de Catalunya 1992
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Castillo, F., Cabestany, J., Moreno, J.M. (1993). Region of influence (ROI) networks. Model and implementation. In: Mira, J., Cabestany, J., Prieto, A. (eds) New Trends in Neural Computation. IWANN 1993. Lecture Notes in Computer Science, vol 686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56798-4_130
Download citation
DOI: https://doi.org/10.1007/3-540-56798-4_130
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56798-1
Online ISBN: 978-3-540-47741-9
eBook Packages: Springer Book Archive