Intelligent system for automatic feature detection and selection or identification

Sun, C T; Shiang, P S; Jang, J S; Fu, C Y

Title: Intelligent system for automatic feature detection and selection or identification

Full Record
Other Related Research

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 (n{minus}1)`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 shown in Equation 1 where N{sub k{minus}1} is the number of nodes in layer k{minus}1, i indexes the nodes of layer k{minus}1 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{sub 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 n{minus}1} in layer n{minus}1. W{sub n,j} (i,p{sub n,j,1}, . . . , p{sub n,j},Pn) can be convex in i, and it can be bell-shaped. Sample functions for w{sub n,j} (i, p{sub n,j,1}, . . . , p{sub n,j},Pn) include Equation 2, shown in the patent. 8 figs.

Inventors:: Sun, C T; Shiang, P S; Jang, J S; Fu, C Y

Publication Date:: Tue Sep 02 00:00:00 EDT 1997

Research Org.:: Univ. of California (United States)

OSTI Identifier:: 527782

Patent Number(s):: US 5,664,066/A/

Application Number:: PAN: 8-304,660

Assignee:: Dept. of Energy, Washington, DC (United States)

DOE Contract Number:: W-7405-ENG-48

Resource Type:: Patent

Resource Relation:: Other Information: PBD: 2 Sep 1997

Country of Publication:: United States

Language:: English

Subject:: 99 MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS; NEURAL NETWORKS; IDENTIFICATION SYSTEMS; FUZZY LOGIC; TRAINING; WEIGHTING FUNCTIONS

Citation Formats


                    Sun, C T, Shiang, P S, Jang, J S, and Fu, C Y. Intelligent system for automatic feature detection and selection or identification.  United States: N. p., 1997. 
        Web.

Copy to clipboard


                    Sun, C T, Shiang, P S, Jang, J S, & Fu, C Y. Intelligent system for automatic feature detection and selection or identification.  United States.

Copy to clipboard


                    Sun, C T, Shiang, P S, Jang, J S, and Fu, C Y. 1997.  
        "Intelligent system for automatic feature detection and selection or identification".  United States.

Copy to clipboard


                    
@article{osti_527782,

  title        = {Intelligent system for automatic feature detection and selection or identification},

  author       = {Sun, C T and Shiang, P S and Jang, J S and Fu, C Y},

  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 (n{minus}1)`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 shown in Equation 1 where N{sub k{minus}1} is the number of nodes in layer k{minus}1, i indexes the nodes of layer k{minus}1 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{sub 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 n{minus}1} in layer n{minus}1. W{sub n,j} (i,p{sub n,j,1}, . . . , p{sub n,j},Pn) can be convex in i, and it can be bell-shaped. Sample functions for w{sub n,j} (i, p{sub n,j,1}, . . . , p{sub n,j},Pn) include Equation 2, shown in the patent. 8 figs.},

  doi          = {},

  url          = {https://www.osti.gov/biblio/527782},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {Tue Sep 02 00:00:00 EDT 1997},

  month        = {Tue Sep 02 00:00:00 EDT 1997}

}

Copy to clipboard

Patent:

Search for the full text at the U.S. Patent and Trademark Office

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Intelligent system for automatic feature detection and selection or identification

Patent Sun, Chuen-Tsai; Jang, Jyh-Shing; Fu, Chi-Yung

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 (n-1)'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.k-1 is the number of nodes in layer k-1, i indexes the nodes of layer k-1 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,more »« less
Full Text Available
Short term daily average and peak load predications using a hybrid intelligent approach

Conference Dash, P; Satpathy, H; Rahman, S

A fuzzy neural network based on the multilayer perceptron and capable of fuzzy classification of patterns is presented in this paper. A hybrid learning algorithm consisting of unsupervised and supervised learning phases is used for training the network. In the supervised learning phase linear Kalman filter equations are used for tuning the weights and membership functions. Extensive tests have been performed on two-year utility data for generation of peak and average load profiles for 24- and 168-hours ahead time frames and results for winter and summer months are given to confirm the effectiveness of the new approach.
PHYSICS DIVISION SEMIANNUAL PROGRESS REPORT FOR PERIOD ENDING MARCH 10, 1958

Technical Report

A new formalism is described which allows the consistent introduction into relativistic quantum theory of a cut-off momentum without use of an arbitary form factor. Information on the gamma decay characteristics is obtained for the second 2/sup +/ states of W, Os, and Pt nuclei. The total neutron cross sections for C/sup 12/, C/sup 13/, and Ne/sup 21/ were measured. The S/sup 32/(n, alpha )Si/sup 29/ cross section was measured relative to the fission cross section of U/ sup 238/ as a function of incident neutron energy in the range 1.3 < E/sub n/, < 3.8 Mev. Total neutron crossmore »« less
https://doi.org/10.2172/4342001

Full Text Available
Eightfold way from dynamical first principles in strongly coupled lattice quantum chromodynamics

Journal Article Faria da Veiga, Paulo; O'Carroll, Michael - Journal of Mathematical Physics

We obtain from first principles, i.e., from the quark-gluon dynamics, the Gell'Mann-Ne'eman baryonic eightfold way energy momentum spectrum exactly in an imaginary-time functional integral formulation of strongly coupled lattice quantum chromodynamics in 3+1 dimensions, with local SU(3){sub c} gauge and global SU(3){sub f} flavor symmetries. We take the hopping parameter {kappa} and the pure gauge coupling {beta} satisfying the strong coupling regime condition 0{<=}{beta}<<{kappa}<<1. The form of the 56 baryon fields emerges naturally from the dynamics and is unveiled using the hyperplane decoupling method. There is no a priori guesswork. In the associated physical quantum mechanical Hilbert space H, spectralmore »« less
https://doi.org/10.1063/1.2804858
Stochastic gradient method for training of a class of recurrent neural nets

Conference Gaivoronski, A; Cazzol, A

A recurrent neural net is defined by set I of nodes, set of input nodes J {contained_in} I, set of output nodes, K {improper_subset} I, set of oriented arcs A {improper_subset} I {times} I. Each node i {element_of} I is characterized by state z{sub i} and function f{sup i} x, z{sub i+} where x is the vector of the network parameters and z{sub i+} is the vector of states of input nodes to node i, i.e. such nodes from which start arcs which point to node i. At the beginning values z{sub i}{sup 0} are assigned to states of allmore »« less

Similar Records