Intelligent system for automatic feature detection and selection or identification
Abstract
A neural network uses a fuzzy membership function, the parameters of which are adaptive during the training process, to parameterize the interconnection weights between an (n1)'th layer and an n'th layer of the network. Each j'th node in each k'th layer of the network except the input layer produces its output value y.sub.k,j according to the function ##EQU1## where N.sub.k1 is the number of nodes in layer k1, i indexes the nodes of layer k1 and all the w.sub.k,i,j are interconnection weights. The interconnection weights to all nodes j in the n'th layer are given by w.sub.n,i,j =w.sub.n,j (i, p.sub.n,j,1, . . . , p.sub.n,j,p.sbsb.n). The apparatus is trained by setting values for at least one of the parameters p.sub.n,j,1, . . . , p.sub.n,j,Pn. Preferably the number of parameters P.sub.n is less than the number of nodes N.sub.n1 in layer n1. w.sub.n,j (i,p.sub.n,j,1, . . . , p.sub.n,j,Pn) can be convex in i, and it can be bellshaped. Sample functions for w.sub.n,j (i, p.sub.n,j,1, . . . , p.sub.n,j,Pn) include ##EQU2##
 Inventors:

 PaoShan Shiang, TW
 Framingham, MA
 San Francisco, CA
 Publication Date:
 Research Org.:
 Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
 OSTI Identifier:
 871136
 Patent Number(s):
 US 5664066
 Assignee:
 United States of America as represented by United States (Washington, DC)
 DOE Contract Number:
 W7405ENG48
 Resource Type:
 Patent
 Country of Publication:
 United States
 Language:
 English
 Subject:
 intelligent; automatic; feature; detection; selection; identification; neural; network; fuzzy; membership; function; parameters; adaptive; training; process; parameterize; interconnection; weights; n1; layer; node; input; produces; output; value; according; equ1; k1; nodes; indexes; sbsb; apparatus; trained; setting; values; pn; preferably; convex; bellshaped; sample; functions; equ2; neural network; training process; feature detection; neural net; output value; /706/
Citation Formats
Sun, ChuenTsai, Jang, JyhShing, and Fu, ChiYung. Intelligent system for automatic feature detection and selection or identification. United States: N. p., 1997.
Web.
Sun, ChuenTsai, Jang, JyhShing, & Fu, ChiYung. Intelligent system for automatic feature detection and selection or identification. United States.
Sun, ChuenTsai, Jang, JyhShing, and Fu, ChiYung. 1997.
"Intelligent system for automatic feature detection and selection or identification". United States. https://www.osti.gov/servlets/purl/871136.
@article{osti_871136,
title = {Intelligent system for automatic feature detection and selection or identification},
author = {Sun, ChuenTsai and Jang, JyhShing and Fu, ChiYung},
abstractNote = {A neural network uses a fuzzy membership function, the parameters of which are adaptive during the training process, to parameterize the interconnection weights between an (n1)'th layer and an n'th layer of the network. Each j'th node in each k'th layer of the network except the input layer produces its output value y.sub.k,j according to the function ##EQU1## where N.sub.k1 is the number of nodes in layer k1, i indexes the nodes of layer k1 and all the w.sub.k,i,j are interconnection weights. The interconnection weights to all nodes j in the n'th layer are given by w.sub.n,i,j =w.sub.n,j (i, p.sub.n,j,1, . . . , p.sub.n,j,p.sbsb.n). The apparatus is trained by setting values for at least one of the parameters p.sub.n,j,1, . . . , p.sub.n,j,Pn. Preferably the number of parameters P.sub.n is less than the number of nodes N.sub.n1 in layer n1. w.sub.n,j (i,p.sub.n,j,1, . . . , p.sub.n,j,Pn) can be convex in i, and it can be bellshaped. Sample functions for w.sub.n,j (i, p.sub.n,j,1, . . . , p.sub.n,j,Pn) include ##EQU2##},
doi = {},
url = {https://www.osti.gov/biblio/871136},
journal = {},
number = ,
volume = ,
place = {United States},
year = {1997},
month = {1}
}
Works referenced in this record:
A method for selfdetermination of adaptive learning rates in back propagation
journal, January 1991
 Weir, Michael K.
 Neural Networks, Vol. 4, Issue 3
Neuralnetworkbased fuzzy logic control and decision system
journal, January 1991
 Lin, C. T.; Lee, C. S. G.
 IEEE Transactions on Computers, Vol. 40, Issue 12
Initializing multilayer neural networks with fuzzy logic
conference, January 1992
 Okada, H.; Watanabe, N.; Kawamura, A.
 [1992] IJCNN International Joint Conference on Neural Networks, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks
An introduction to computing with neural nets
journal, January 1987
 Lippmann, R.
 IEEE ASSP Magazine, Vol. 4, Issue 2
Rescaling of variables in back propagation learning
journal, January 1991
 Rigler, A. K.; Irvine, J. M.; Vogl, T. P.
 Neural Networks, Vol. 4, Issue 2
ANFIS: adaptivenetworkbased fuzzy inference system
journal, January 1993
 Jang, J. S. R.
 IEEE Transactions on Systems, Man, and Cybernetics, Vol. 23, Issue 3
Backpropagation algorithm which varies the number of hidden units
journal, January 1991
 Hirose, Yoshio; Yamashita, Koichi; Hijiya, Shimpei
 Neural Networks, Vol. 4, Issue 1
A prototype of neurofuzzy cooperation system
conference, January 1992
 Kawamura, A.; Watanabe, N.; Okada, H.
 [1992 Proceedings] IEEE International Conference on Fuzzy Systems
Fuzzy logic in control systems: fuzzy logic controller. II
journal, January 1990
 Lee, C. C.
 IEEE Transactions on Systems, Man, and Cybernetics, Vol. 20, Issue 2