ES2073567T3 - Red de proceso distribuido paralelo en que los pesos de conexion se generan mediante la utilizacion de ecuaciones diferenciales con coeficientes constantes. - Google Patents

Red de proceso distribuido paralelo en que los pesos de conexion se generan mediante la utilizacion de ecuaciones diferenciales con coeficientes constantes.

Info

Publication number
ES2073567T3
ES2073567T3 ES90905374T ES90905374T ES2073567T3 ES 2073567 T3 ES2073567 T3 ES 2073567T3 ES 90905374 T ES90905374 T ES 90905374T ES 90905374 T ES90905374 T ES 90905374T ES 2073567 T3 ES2073567 T3 ES 2073567T3
Authority
ES
Spain
Prior art keywords
differential equations
connection weights
generated
parallel distributed
process network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
ES90905374T
Other languages
English (en)
Inventor
David Lee Filken
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
EIDP Inc
Original Assignee
EI Du Pont de Nemours and Co
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by EI Du Pont de Nemours and Co filed Critical EI Du Pont de Nemours and Co
Application granted granted Critical
Publication of ES2073567T3 publication Critical patent/ES2073567T3/es
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0499—Feedforward networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Paper (AREA)
  • Complex Calculations (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Image Analysis (AREA)
  • Lift-Guide Devices, And Elevator Ropes And Cables (AREA)
  • Multi Processors (AREA)
  • Hardware Redundancy (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Electrical Discharge Machining, Electrochemical Machining, And Combined Machining (AREA)

Abstract

SE REVELA UNA RED DE PROCESAMIENTO DISTRIBUIDO PARALELO (10) DE UN TIPO DE PROPAGACION POSTERIOR EN LA QUE LOS PESOS DE CONEXION ENTRE LOS ELEMENTOS DE PROCESAMIENTO (12) EN LAS DIFERENTES CAPAS (14, 16, 18) DE LA RED SE DETERMINAN DE ACUERDO CON LA SERIE DE DISOLUCIONES ESTABLES DE LAS ECUACIONES DIFERENCIALES RIGIDAS QUE REGULAN LA RELACION ENTRE LAS CAPAS DE LA RED.
ES90905374T 1988-12-16 1989-12-13 Red de proceso distribuido paralelo en que los pesos de conexion se generan mediante la utilizacion de ecuaciones diferenciales con coeficientes constantes. Expired - Lifetime ES2073567T3 (es)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US07/285,534 US5046020A (en) 1988-12-16 1988-12-16 Distributed parallel processing network wherein the connection weights are generated using stiff differential equations

Publications (1)

Publication Number Publication Date
ES2073567T3 true ES2073567T3 (es) 1995-08-16

Family

ID=23094658

Family Applications (1)

Application Number Title Priority Date Filing Date
ES90905374T Expired - Lifetime ES2073567T3 (es) 1988-12-16 1989-12-13 Red de proceso distribuido paralelo en que los pesos de conexion se generan mediante la utilizacion de ecuaciones diferenciales con coeficientes constantes.

Country Status (10)

Country Link
US (1) US5046020A (es)
EP (1) EP0449994B1 (es)
JP (1) JPH0760428B2 (es)
KR (1) KR930004438B1 (es)
AT (1) ATE122483T1 (es)
AU (1) AU5411090A (es)
CA (1) CA2005370A1 (es)
DE (1) DE68922624T2 (es)
ES (1) ES2073567T3 (es)
WO (1) WO1990007158A1 (es)

Families Citing this family (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2533942B2 (ja) * 1989-03-13 1996-09-11 株式会社日立製作所 知識抽出方法およびプロセス運転支援システム
DE68927675T2 (de) * 1989-08-23 1997-07-10 Hitachi Ltd Verfahren zur Richtigstellung von Netzwerkwichtungsfaktoren in einer mehrschichtigen Perceptronvorrichtung und eine solche Vorrichtung mit Mitteln zur Ausführung dieses Verfahrens
GB8929146D0 (en) * 1989-12-22 1990-02-28 British Telecomm Neural networks
US5167006A (en) * 1989-12-29 1992-11-24 Ricoh Company, Ltd. Neuron unit, neural network and signal processing method
US5581662A (en) * 1989-12-29 1996-12-03 Ricoh Company, Ltd. Signal processing apparatus including plural aggregates
JPH03250243A (ja) * 1990-02-27 1991-11-08 Toshiba Corp 神経回路網演算装置
JP2540654B2 (ja) * 1990-06-28 1996-10-09 シャープ株式会社 ニュ―ラルネットワ―クの学習装置
JP2763182B2 (ja) * 1990-06-28 1998-06-11 株式会社東芝 ニューラル・ネットワークの学習方法
GB2246895B (en) * 1990-07-12 1994-03-30 Mitsubishi Electric Corp Neural network system
JPH04266153A (ja) * 1991-02-20 1992-09-22 Honda Motor Co Ltd ニューラルネットワーク
US5331550A (en) * 1991-03-05 1994-07-19 E. I. Du Pont De Nemours And Company Application of neural networks as an aid in medical diagnosis and general anomaly detection
US5157275A (en) * 1991-03-22 1992-10-20 Ricoh Corporation Circuit employing logical gates for calculating activation function derivatives on stochastically-encoded signals
US5528729A (en) * 1991-06-12 1996-06-18 Ricoh Company, Ltd. Neural network learning apparatus and learning method
JPH05128085A (ja) * 1991-11-08 1993-05-25 Toshiba Corp システム制御の学習方法
CA2081036C (en) * 1991-12-19 1999-08-03 Ahmed Hashem Abdelmonem Method and apparatus for predicting transmission system errors and failures
WO1993019426A1 (en) * 1992-03-25 1993-09-30 Western Mining Corporation Limited Method of detecting and mapping minerals and other geological phenomena utilizing airborne imaging spectrometers
ATE279758T1 (de) * 1992-06-19 2004-10-15 United Parcel Service Inc Verfahren und gerät zur einstellung eines neurons
US5428710A (en) * 1992-06-29 1995-06-27 The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration Fast temporal neural learning using teacher forcing
US5598509A (en) * 1992-08-28 1997-01-28 Hitachi, Ltd. Method of configuring a neural network and a diagnosis/recognition system using the same
JPH06274660A (ja) * 1993-03-18 1994-09-30 Hitachi Ltd 認識又は診断方法
US5288645A (en) * 1992-09-04 1994-02-22 Mtm Engineering, Inc. Hydrogen evolution analyzer
US5742702A (en) * 1992-10-01 1998-04-21 Sony Corporation Neural network for character recognition and verification
US5319722A (en) * 1992-10-01 1994-06-07 Sony Electronics, Inc. Neural network for character recognition of rotated characters
US5930781A (en) * 1992-10-27 1999-07-27 The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration Neural network training by integration of adjoint systems of equations forward in time
US5517667A (en) * 1993-06-14 1996-05-14 Motorola, Inc. Neural network that does not require repetitive training
US5920852A (en) * 1996-04-30 1999-07-06 Grannet Corporation Large memory storage and retrieval (LAMSTAR) network
US7215811B2 (en) * 2000-11-22 2007-05-08 Osama Moselhi Method and apparatus for the automated detection and classification of defects in sewer pipes
US20060031027A1 (en) * 2004-08-03 2006-02-09 Alman David H Method and apparatus for predicting properties of a chemical mixture
TW200928793A (en) * 2007-12-26 2009-07-01 Ruei-Jau Chen Algorithm method capable of enhancing accuracy and computation speed of the computation of corrected sums of products (CSP) of computing hardware
US8218904B2 (en) * 2008-08-27 2012-07-10 Lockheed Martin Corporation Method and system for circular to horizontal transposition of an image
US10192016B2 (en) * 2017-01-17 2019-01-29 Xilinx, Inc. Neural network based physical synthesis for circuit designs
US11922314B1 (en) * 2018-11-30 2024-03-05 Ansys, Inc. Systems and methods for building dynamic reduced order physical models
AR118333A1 (es) 2019-03-18 2021-09-29 Evonik Operations Gmbh Método para generar una composición para pinturas, barnices, tintas de impresión, resinas de molienda, concentrados de pigmentos u otros materiales de recubrimiento

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4773024A (en) * 1986-06-03 1988-09-20 Synaptics, Inc. Brain emulation circuit with reduced confusion
WO1988007234A1 (en) * 1987-03-12 1988-09-22 Analog Intelligence Corporation Back propagation system

Also Published As

Publication number Publication date
DE68922624T2 (de) 1995-10-19
EP0449994B1 (en) 1995-05-10
JPH04503274A (ja) 1992-06-11
KR910700501A (ko) 1991-03-15
AU5411090A (en) 1990-07-10
ATE122483T1 (de) 1995-05-15
EP0449994A4 (en) 1992-04-29
CA2005370A1 (en) 1990-06-16
WO1990007158A1 (en) 1990-06-28
KR930004438B1 (en) 1993-05-27
US5046020A (en) 1991-09-03
EP0449994A1 (en) 1991-10-09
JPH0760428B2 (ja) 1995-06-28
DE68922624D1 (de) 1995-06-14

Similar Documents

Publication Publication Date Title
KR910700501A (ko) 접속 가중치가 풀기어려운 미분 방정식을 사용하여 발생된 병렬 분포 프로세싱 네트워크
ES2060611T3 (es) Fotoiniciadores correactivos.
ES2073431T3 (es) Miembro de lamina que contiene una pluralidad de canales alargados, encerrados, electrodepositados y metodo.
IT1111874B (it) Pezzo intermedio con un detettore di luce per un collegamento disimpegnabile ad innesto,impiegato per il collegamento di una fibra per la conduzione di luce con una sorgente di luce a semiconduttore
FI844341L (fi) Buffertsystem foer input/output delen i ett digitalt databehandlingssystem.
MX164447B (es) Vacuempacado,y empaque obtenido mediante los mismos
AR001440A1 (es) Nuevos taxoides, su preparación y composiciones farmacéuticas que los contienen.
ATE192245T1 (de) In der grundzahl 4 arbeitende übertragvorgriffsbäume
NO157853C (no) Barberhoevelhode.
FI843392A7 (fi) (substituerade)fenyl-alifatiska isoxazoler anvaendbara som antivirala aemnen och deras framstaellning.
IT7922462A0 (it) Copolimero ad innesto utile nella elettrodeposizione.
IT8222421V0 (it) Serie omogenea di due modelli ornamentali comprendente una antipastiera a vaschette amovibili ed un bicchiere presentanti entrambi porzioni contrapposte a righe parallele.
IT8125809A0 (it) Disposizione circuitale atta a collegare una pluralita' di coppie di elaboratori ad un ulteriore coppia di elaboratori di gerarchia superiore.
ES8308178A1 (es) Un filtro de equilibrio del tipo de respuesta de impulsos finitos, destinado a utilizarse en un sistema de telecomunicacion.
DE3888601D1 (de) Halbleiterlaser mit konstanter differentieller Quantenausbeute oder konstanter optischer Ausgangsleistung.
AU560108B2 (en) Balanced output differential amplifier
ES530797A0 (es) Procedimiento en las placas de retencion del cubo principal de helicopteros.
SE9400318L (sv) Anordning för sammanlagring av fyra mikrovågssignaler samt magiskt T för användning i anordningen
BG37078A3 (en) Method for preparing 6- methyl- 4. 6- 3- ketosteroides
FI841686L (fi) Foerfarande foer bestaemning av katepsin b i naervaro av andra proteolytiska enzymer och foereningar anvaendbara daerfoer.
SU872166A1 (ru) Способ восстановлени изношенной поверхности изделий
SU917177A1 (ru) Регул тор уровн нижнего бьефа
JPS5754379A (en) Selecting method for light-emitting element
IT8049454A0 (it) Perfezionamento negli apparecchi per la generazione di superfici ottiche in particolare per lenti
ES2015483A6 (es) Transductor interdigital de ondas superficiales y filtro de ondas superficiales con caracteristica de transmision simetrica o asimetrica predeterminable entre entrada y salida.

Legal Events

Date Code Title Description
FG2A Definitive protection

Ref document number: 449994

Country of ref document: ES