Neural node network and model, and method of teaching same

Parlos, Alexander G.; Atiya, Amir F.; Fernandez, Benito; Tsai, Wei K.; Chong, Kil T.

Advanced Search OptionsAdvanced Search queries use a traditional Term Search. For more info, see our FAQ.

All Fields:

Patent Title:

Abstract:

Assignee:

Inventor(s):

Patent Number:

Patent Classification (CPC):

All Classifications
A - human necessities
A01 - agriculture
A21 - baking
A22 - butchering
A23 - foods or foodstuffs
A24 - tobacco
A41 - wearing apparel
A42 - headwear
A43 - footwear
A44 - haberdashery
A45 - hand or travelling articles
A46 - brushware
A47 - furniture
A61 - medical or veterinary science
A62 - life-saving
A63 - sports
A99 - subject matter not otherwise provided for in this section
B - performing operations
B01 - physical or chemical processes or apparatus in general
B02 - crushing, pulverising, or disintegrating
B03 - separation of solid materials using liquids or using pneumatic tables or jigs
B04 - centrifugal apparatus or machines for carrying-out physical or chemical processes
B05 - spraying or atomising in general
B06 - generating or transmitting mechanical vibrations in general
B07 - separating solids from solids
B08 - cleaning
B09 - disposal of solid waste
B21 - mechanical metal-working without essentially removing material
B22 - casting
B23 - machine tools
B24 - grinding
B25 - hand tools
B26 - hand cutting tools
B27 - working or preserving wood or similar material
B28 - working cement, clay, or stone
B29 - working of plastics
B30 - presses
B31 - making articles of paper, cardboard or material worked in a manner analogous to paper
B32 - layered products
B33 - additive manufacturing technology
B41 - printing
B42 - bookbinding
B43 - writing or drawing implements
B44 - decorative arts
B60 - vehicles in general
B61 - railways
B62 - land vehicles for travelling otherwise than on rails
B63 - ships or other waterborne vessels
B64 - aircraft
B65 - conveying
B66 - hoisting
B67 - opening, closing {or cleaning} bottles, jars or similar containers
B68 - saddlery
B81 - microstructural technology
B82 - nanotechnology
B99 - subject matter not otherwise provided for in this section
C - chemistry
C01 - inorganic chemistry
C02 - treatment of water, waste water, sewage, or sludge
C03 - glass
C04 - cements
C05 - fertilisers
C06 - explosives
C07 - organic chemistry
C08 - organic macromolecular compounds
C09 - dyes
C10 - petroleum, gas or coke industries
C11 - animal or vegetable oils, fats, fatty substances or waxes
C12 - biochemistry
C13 - sugar industry
C14 - skins
C21 - metallurgy of iron
C22 - metallurgy
C23 - coating metallic material
C25 - electrolytic or electrophoretic processes
C30 - crystal growth
C40 - combinatorial technology
C99 - subject matter not otherwise provided for in this section
D - textiles
D01 - natural or man-made threads or fibres
D02 - yarns
D03 - weaving
D04 - braiding
D05 - sewing
D06 - treatment of textiles or the like
D07 - ropes
D10 - indexing scheme associated with sublasses of section d, relating to textiles
D21 - paper-making
D99 - subject matter not otherwise provided for in this section
E - fixed constructions
E01 - construction of roads, railways, or bridges
E02 - hydraulic engineering
E03 - water supply
E04 - building
E05 - locks
E06 - doors, windows, shutters, or roller blinds in general
E21 - earth drilling
E99 - subject matter not otherwise provided for in this section
F - mechanical engineering
F01 - machines or engines in general
F02 - combustion engines
F03 - machines or engines for liquids
F04 - positive - displacement machines for liquids
F05 - indexing schemes relating to engines or pumps in various subclasses of classes f01-f04
F15 - fluid-pressure actuators
F16 - engineering elements and units
F17 - storing or distributing gases or liquids
F21 - lighting
F22 - steam generation
F23 - combustion apparatus
F24 - heating
F25 - refrigeration or cooling
F26 - drying
F27 - furnaces
F28 - heat exchange in general
F41 - weapons
F42 - ammunition
F99 - subject matter not otherwise provided for in this section
G - physics
G01 - measuring
G02 - optics
G03 - photography
G04 - horology
G05 - controlling
G06 - computing
G07 - checking-devices
G08 - signalling
G09 - education
G10 - musical instruments
G11 - information storage
G12 - instrument details
G16 - information and communication technology [ict] specially adapted for specific application fields
G21 - nuclear physics
G99 - subject matter not otherwise provided for in this section
H - electricity
H01 - basic electric elements
H02 - generation
H03 - basic electronic circuitry
H04 - electric communication technique
H05 - electric techniques not otherwise provided for
H99 - subject matter not otherwise provided for in this section
Y - new / cross sectional technologies
Y02 - technologies or applications for mitigation or adaptation against climate change
Y04 - information or communication technologies having an impact on other technology areas
Y10 - technical subjects covered by former uspc

More Options ...

Title: Neural node network and model, and method of teaching same

Abstract

The present invention is a fully connected feed forward network that includes at least one hidden layer 16. The hidden layer 16 includes nodes 20 in which the output of the node is fed back to that node as an input with a unit delay produced by a delay device 24 occurring in the feedback path 22 (local feedback). Each node within each layer also receives a delayed output (crosstalk) produced by a delay unit 36 from all the other nodes within the same layer 16. The node performs a transfer function operation based on the inputs from the previous layer and the delayed outputs. The network can be implemented as analog or digital or within a general purpose processor. Two teaching methods can be used: (1) back propagation of weight calculation that includes the local feedback and the crosstalk or (2) more preferably a feed forward gradient decent which immediately follows the output computations and which also includes the local feedback and the crosstalk. Subsequent to the gradient propagation, the weights can be normalized, thereby preventing convergence to a local optimum. Education of the network can be incremental both on and off-line. An educated network is suitable for modelingmore » « less

Inventors:: Parlos, Alexander G.; Atiya, Amir F.; Fernandez, Benito; Tsai, Wei K.; Chong, Kil T.

Issue Date:: 1995-01-01

Research Org.:: Texas A&M Univ., College Station, TX (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 870229

Patent Number(s):: 5479571

Application Number:: 08/046,936

Assignee:: The Texas A&M University System (College Station, TX)

Patent Classifications (CPCs):: G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

Show more

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G06N3/049 - {Temporal neural nets, e.g. delay elements, oscillating neurons, pulsed inputs}

Show less

DOE Contract Number:: FG07-89ER12893

Resource Type:: Patent

Resource Relation:: Patent File Date: 1993 Apr 13

Country of Publication:: United States

Language:: English

Subject:: /706/

Citation Formats


                    Parlos, Alexander G., Atiya, Amir F., Fernandez, Benito, Tsai, Wei K., and Chong, Kil T. Neural node network and model, and method of teaching same.  United States: N. p., 1995. 
        Web.

Copy to clipboard


                    Parlos, Alexander G., Atiya, Amir F., Fernandez, Benito, Tsai, Wei K., & Chong, Kil T. Neural node network and model, and method of teaching same.  United States.

Copy to clipboard


                    Parlos, Alexander G., Atiya, Amir F., Fernandez, Benito, Tsai, Wei K., and Chong, Kil T. Sun .  
        "Neural node network and model, and method of teaching same".  United States.  https://www.osti.gov/servlets/purl/870229.

Copy to clipboard


                    
@article{osti_870229,

  title        = {Neural node network and model, and method of teaching same},

  author       = {Parlos, Alexander G. and Atiya, Amir F. and Fernandez, Benito and Tsai, Wei K. and Chong, Kil T.},

  abstractNote = {The present invention is a fully connected feed forward network that includes at least one hidden layer 16. The hidden layer 16 includes nodes 20 in which the output of the node is fed back to that node as an input with a unit delay produced by a delay device 24 occurring in the feedback path 22 (local feedback). Each node within each layer also receives a delayed output (crosstalk) produced by a delay unit 36 from all the other nodes within the same layer 16. The node performs a transfer function operation based on the inputs from the previous layer and the delayed outputs. The network can be implemented as analog or digital or within a general purpose processor. Two teaching methods can be used: (1) back propagation of weight calculation that includes the local feedback and the crosstalk or (2) more preferably a feed forward gradient decent which immediately follows the output computations and which also includes the local feedback and the crosstalk. Subsequent to the gradient propagation, the weights can be normalized, thereby preventing convergence to a local optimum. Education of the network can be incremental both on and off-line. An educated network is suitable for modeling and controlling dynamic nonlinear systems and time series systems and predicting the outputs as well as hidden states and parameters. The educated network can also be further educated during on-line processing.},

  doi          = {},

  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {1995},

  month        = {1}

}

Copy to clipboard

Patent:

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Neural networks and physical systems with emergent collective computational abilities.
journal, April 1982

Hopfield, J. J.
Proceedings of the National Academy of Sciences, Vol. 79, Issue 8
https://doi.org/10.1073/pnas.79.8.2554

Generalization of back-propagation to recurrent neural networks
journal, November 1987

Pineda, Fernando J.
Physical Review Letters, Vol. 59, Issue 19
https://doi.org/10.1103/PhysRevLett.59.2229

Approximation by superpositions of a sigmoidal function
journal, December 1989

Cybenko, G.
Mathematics of Control, Signals, and Systems, Vol. 2, Issue 4
https://doi.org/10.1007/BF02551274

Learning state space trajectories in recurrent neural networks
conference, January 1989

Pearlmutter, Barak A.
International Joint Conference on Neural Networks
https://doi.org/10.1109/IJCNN.1989.118724

Parallel Distributed Processing
book, January 1986

Rumelhart, David E.; McClelland, James L.
https://doi.org/10.7551/mitpress/5236.001.0001

Adaptation and tracking in system identification—A survey
journal, January 1990

Ljung, Lennart; Gunnarsson, Svante
Automatica, Vol. 26, Issue 1
https://doi.org/10.1016/0005-1098(90)90154-A

Benefits of gain: speeded learning and minimal hidden layers in back-propagation networks
journal, January 1991

Kruschke, J. K.; Movellan, J. R.
IEEE Transactions on Systems, Man, and Cybernetics, Vol. 21, Issue 1
https://doi.org/10.1109/21.101159

Issues in system identification
journal, January 1991

Ljung, L.
IEEE Control Systems, Vol. 11, Issue 1, p. 25-29
https://doi.org/10.1109/37.103346

Complex temporal sequence learning based on short-term memory
journal, January 1990

Wang, D.; Arbib, M. A.
Proceedings of the IEEE, Vol. 78, Issue 9
https://doi.org/10.1109/5.58329

Self-organizing network for optimum supervised learning
journal, March 1990

Tenorio, M. F.; Lee, W. -T.
IEEE Transactions on Neural Networks, Vol. 1, Issue 1
https://doi.org/10.1109/72.80209

Structure identification of nonlinear dynamic systems—A survey on input/output approaches
journal, July 1990

Haber, R.; Unbehauen, H.
Automatica, Vol. 26, Issue 4
https://doi.org/10.1016/0005-1098(90)90044-I

Chaotic dynamics of time-delay neural networks
conference, January 1990

Principe, J. C.; Lo, P. -C.
1990 IJCNN International Joint Conference on Neural Networks
https://doi.org/10.1109/IJCNN.1990.137746

Neural networks for system identification
journal, April 1990

Chu, S. R.; Shoureshi, R.; Tenorio, M.
IEEE Control Systems Magazine, Vol. 10, Issue 3
https://doi.org/10.1109/37.55121

Identification and control of dynamical systems using neural networks
journal, March 1990

Narendra, K. S.; Parthasarathy, K.
IEEE Transactions on Neural Networks, Vol. 1, Issue 1
https://doi.org/10.1109/72.80202

Nonlinear dynamic system identification using artificial neural networks (ANNs)
conference, January 1990

Fernandez, B.; Parlos, A. G.; Tsai, W. K.
1990 IJCNN International Joint Conference on Neural Networks
https://doi.org/10.1109/IJCNN.1990.137706

Recurrent Backpropagation and the Dynamical Approach to Adaptive Neural Computation
journal, June 1989

Pineda, Fernando J.
Neural Computation, Vol. 1, Issue 2
https://doi.org/10.1162/neco.1989.1.2.161

A comparison of the backpropagation and recursive prediction error algorithms for training neural networks
journal, May 1991

Billings, S. A.; Jamaluddin, H. B.; Chen, S.
Mechanical Systems and Signal Processing, Vol. 5, Issue 3
https://doi.org/10.1016/0888-3270(91)90045-7

An accelerated learning algorithm for multilayer perceptron networks
journal, May 1994

Parlos, A. G.; Fernandez, B.; Atiya, A. F.
IEEE Transactions on Neural Networks, Vol. 5, Issue 3
https://doi.org/10.1109/72.286921

A recurrent time-delay neural network for improved phoneme recognition
conference, January 1991

Greco, F.; Paoloni, A.; Ravaioli, G.
[Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing
https://doi.org/10.1109/ICASSP.1991.150283

Backpropagation through time: what it does and how to do it
journal, January 1990

Werbos, P. J.
Proceedings of the IEEE, Vol. 78, Issue 10
https://doi.org/10.1109/5.58337

Principal component analysis by gradient descent on a constrained linear Hebbian cell
conference, January 1989

Chauvin, K. M.
International Joint Conference on Neural Networks
https://doi.org/10.1109/IJCNN.1989.118611

Speaker-independent recognition of connected utterances using recurrent and non-recurrent neural networks
conference, January 1989

Franzini, M.; Witbrock, Michael; Lee, T. H.
International Joint Conference on Neural Networks
https://doi.org/10.1109/IJCNN.1989.118670

Use of neural nets for dynamic modeling and control of chemical process systems
journal, May 1990

Bhat, N.; McAvoy, T. J.
Computers & Chemical Engineering, Vol. 14, Issue 4-5
https://doi.org/10.1016/0098-1354(90)87028-N

Bounding the states of systems with unknown-but-bounded disturbances
journal, October 1990

Tsai, Wei K.; Parlos, Alexander G.; Verghese, George C.
International Journal of Control, Vol. 52, Issue 4
https://doi.org/10.1080/00207179008953573

Identification of nonlinear systems–a survey
journal, January 1980

Billings, S. A.
IEE Proceedings D Control Theory and Applications, Vol. 127, Issue 6
https://doi.org/10.1049/ip-d.1980.0047

Learning by parallel forward propagation
conference, January 1990

Abe, S.
1990 IJCNN International Joint Conference on Neural Networks
https://doi.org/10.1109/IJCNN.1990.137830

A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
journal, June 1989

Williams, Ronald J.; Zipser, David
Neural Computation, Vol. 1, Issue 2
https://doi.org/10.1162/neco.1989.1.2.270

An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories
journal, December 1990

Williams, Ronald J.; Peng, Jing
Neural Computation, Vol. 2, Issue 4
https://doi.org/10.1162/neco.1990.2.4.490

Similar Records in DOE Patents and OSTI.GOV collections:

Neural node network and model, and method of teaching same

Patent Parlos, A G; Atiya, A F; Fernandez, B; ...

The present invention is a fully connected feed forward network that includes at least one hidden layer. The hidden layer includes nodes in which the output of the node is fed back to that node as an input with a unit delay produced by a delay device occurring in the feedback path (local feedback). Each node within each layer also receives a delayed output (crosstalk) produced by a delay unit from all the other nodes within the same layer. The node performs a transfer function operation based on the inputs from the previous layer and the delayed outputs. The networkmore » « less
Channel hopping method of interference avoidance for a wireless communication network and wireless communication system employing the same

Patent Rentel, Carlos H.; Pereira, Luis R.; Gutierrez, Jose A.

A wireless communication system includes a wireless master node having a plurality of channels, and a number of wireless slave nodes having a plurality of the channels. The master node and the slave nodes are structured to wirelessly communicate over a particular channel. The master node and the slave nodes are structured to decide to hop to a different channel. The master node and the slave nodes are structured to select: (a) the different channel, in order to be as far away as possible from a number of the channels, which are known to cause interference to wireless communications betweenmore » « less
Full Text Available
Controller architecture and systems and methods for implementing the same in a networked control system

Patent Wyman, Richard P.

An architecture for a control system in a network, and devices and techniques for implementing the same. The architecture may comprise a logic controller isolated from the network by an interface controller and a bridge interface between the interface controller and the logic controller.
Full Text Available
Network and topology for identifying, locating and quantifying physical phenomena, systems and methods for employing same

Patent Richardson, John G.; Moore, Karen A.; Carrington, Robert A.

A method and system for detecting, locating and quantifying a physical phenomena such as strain or a deformation in a structure. A plurality of laterally adjacent conductors may each include a plurality of segments. Each segment is constructed to exhibit a unit value representative of a defined energy transmission characteristic. A plurality of identity groups are defined with each identity group comprising a plurality of segments including at least one segment from each of the plurality of conductors. The segments contained within an identity group are configured and arranged such that each of their associated unit values may be representedmore » « less
Full Text Available
Interpenetrating polymer network ion exchange membranes and method for preparing same

Patent Alexandratos, Spiro D [Knoxville, TN]; Danesi, Pier R [Vienna, AT]; Horwitz, E Philip [Naperville, IL]

Interpenetrating polymer network ion exchange membranes include a microporous polymeric support film interpenetrated by an ion exchange polymer and are produced by absorbing and polymerizing monomers within the support film. The ion exchange polymer provides ion exchange ligands at the surface of and throughout the support film which have sufficient ligand mobility to extract and transport ions across the membrane.
Full Text Available

Similar Records

Title: Neural node network and model, and method of teaching same

Abstract

Citation Formats

Neural networks and physical systems with emergent collective computational abilities. journal, April 1982

Generalization of back-propagation to recurrent neural networks journal, November 1987

Approximation by superpositions of a sigmoidal function journal, December 1989

Learning state space trajectories in recurrent neural networks conference, January 1989

Parallel Distributed Processing book, January 1986

Adaptation and tracking in system identification—A survey journal, January 1990

Benefits of gain: speeded learning and minimal hidden layers in back-propagation networks journal, January 1991

Issues in system identification journal, January 1991

Complex temporal sequence learning based on short-term memory journal, January 1990

Self-organizing network for optimum supervised learning journal, March 1990

Structure identification of nonlinear dynamic systems—A survey on input/output approaches journal, July 1990

Chaotic dynamics of time-delay neural networks conference, January 1990

Neural networks for system identification journal, April 1990

Identification and control of dynamical systems using neural networks journal, March 1990

Nonlinear dynamic system identification using artificial neural networks (ANNs) conference, January 1990

Recurrent Backpropagation and the Dynamical Approach to Adaptive Neural Computation journal, June 1989

A comparison of the backpropagation and recursive prediction error algorithms for training neural networks journal, May 1991

An accelerated learning algorithm for multilayer perceptron networks journal, May 1994

A recurrent time-delay neural network for improved phoneme recognition conference, January 1991

Backpropagation through time: what it does and how to do it journal, January 1990

Principal component analysis by gradient descent on a constrained linear Hebbian cell conference, January 1989

Speaker-independent recognition of connected utterances using recurrent and non-recurrent neural networks conference, January 1989

Use of neural nets for dynamic modeling and control of chemical process systems journal, May 1990

Bounding the states of systems with unknown-but-bounded disturbances journal, October 1990

Identification of nonlinear systems–a survey journal, January 1980

Learning by parallel forward propagation conference, January 1990

A Learning Algorithm for Continually Running Fully Recurrent Neural Networks journal, June 1989

An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories journal, December 1990

Neural networks and physical systems with emergent collective computational abilities.
journal, April 1982

Generalization of back-propagation to recurrent neural networks
journal, November 1987

Approximation by superpositions of a sigmoidal function
journal, December 1989

Learning state space trajectories in recurrent neural networks
conference, January 1989

Parallel Distributed Processing
book, January 1986

Adaptation and tracking in system identification—A survey
journal, January 1990

Benefits of gain: speeded learning and minimal hidden layers in back-propagation networks
journal, January 1991

Issues in system identification
journal, January 1991

Complex temporal sequence learning based on short-term memory
journal, January 1990

Self-organizing network for optimum supervised learning
journal, March 1990

Structure identification of nonlinear dynamic systems—A survey on input/output approaches
journal, July 1990

Chaotic dynamics of time-delay neural networks
conference, January 1990

Neural networks for system identification
journal, April 1990

Identification and control of dynamical systems using neural networks
journal, March 1990

Nonlinear dynamic system identification using artificial neural networks (ANNs)
conference, January 1990

Recurrent Backpropagation and the Dynamical Approach to Adaptive Neural Computation
journal, June 1989

A comparison of the backpropagation and recursive prediction error algorithms for training neural networks
journal, May 1991

An accelerated learning algorithm for multilayer perceptron networks
journal, May 1994

A recurrent time-delay neural network for improved phoneme recognition
conference, January 1991

Backpropagation through time: what it does and how to do it
journal, January 1990

Principal component analysis by gradient descent on a constrained linear Hebbian cell
conference, January 1989

Speaker-independent recognition of connected utterances using recurrent and non-recurrent neural networks
conference, January 1989

Use of neural nets for dynamic modeling and control of chemical process systems
journal, May 1990

Bounding the states of systems with unknown-but-bounded disturbances
journal, October 1990

Identification of nonlinear systems–a survey
journal, January 1980

Learning by parallel forward propagation
conference, January 1990

A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
journal, June 1989

An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories
journal, December 1990