DocumentCode
2618986
Title
Dual networks and their pattern classification properties
Author
Patrikar, Ajay
Author_Institution
Dept. of Electr. Eng., Southern Methodist Univ., Dallas, TX, USA
fYear
1991
fDate
3-6 Jun 1991
Firstpage
686
Lastpage
687
Abstract
An artificial neural network (ANN) architecture termed a dual network is proposed for pattern classification problems. Dual network is a network of densely connected simple processing elements and it presents a structured way to implement polynomial classifiers. A supervised learning algorithm is developed for the dual networks, and their ability to solve complex pattern classification problems is verified through experimental studies
Keywords
learning systems; neural nets; pattern recognition; artificial neural network; dual network; pattern classification; polynomial classifiers; supervised learning algorithm; Artificial neural networks; Ducts; Multi-layer neural network; Multilayer perceptrons; Neural networks; Nonhomogeneous media; Pattern classification; Pattern recognition; Polynomials; Supervised learning;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Conference on
Conference_Location
Maui, HI
ISSN
1063-6919
Print_ISBN
0-8186-2148-6
Type
conf
DOI
10.1109/CVPR.1991.139782
Filename
139782
Link To Document