WO2000003355A3 - Reseau neuronal, et procede et dispositif pour l'entrainement d'un reseau neuronal - Google Patents

Reseau neuronal, et procede et dispositif pour l'entrainement d'un reseau neuronal Download PDF

Info

Publication number
WO2000003355A3
WO2000003355A3 PCT/DE1999/001952 DE9901952W WO0003355A3 WO 2000003355 A3 WO2000003355 A3 WO 2000003355A3 DE 9901952 W DE9901952 W DE 9901952W WO 0003355 A3 WO0003355 A3 WO 0003355A3
Authority
WO
WIPO (PCT)
Prior art keywords
neural net
training
net
neural
trained
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.)
Ceased
Application number
PCT/DE1999/001952
Other languages
German (de)
English (en)
Other versions
WO2000003355A2 (fr
Inventor
Volkmar Sterzing
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.)
Siemens AG
Siemens Corp
Original Assignee
Siemens AG
Siemens Corp
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 Siemens AG, Siemens Corp filed Critical Siemens AG
Priority to EP99942765A priority Critical patent/EP1093639A2/fr
Priority to JP2000559532A priority patent/JP2002520719A/ja
Publication of WO2000003355A2 publication Critical patent/WO2000003355A2/fr
Publication of WO2000003355A3 publication Critical patent/WO2000003355A3/fr
Anticipated expiration legal-status Critical
Ceased 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
    • G06N3/045—Combinations of 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0495—Quantised networks; Sparse networks; Compressed 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
    • G06N3/04—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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • 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)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Feedback Control In General (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

Selon l'invention, dans une première phase d'entraînement, un premier réseau neuronal (102) est entraîné à l'aide d'un premier ensemble de données d'entraînement. Le premier réseau neuronal et un second réseau neuronal (103) sont, dans une seconde phase d'entraînement, entraînés avec un second ensemble de données d'entraînement, des paramètres du premier réseau neuronal restant inchangés dans la seconde phase d'entraînement.
PCT/DE1999/001952 1998-07-08 1999-07-01 Reseau neuronal, et procede et dispositif pour l'entrainement d'un reseau neuronal Ceased WO2000003355A2 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP99942765A EP1093639A2 (fr) 1998-07-08 1999-07-01 Reseau neuronal, et procede et dispositif pour l'entrainement d'un reseau neuronal
JP2000559532A JP2002520719A (ja) 1998-07-08 1999-07-01 ニューラルネット及びニューラルネットのトレーニング方法及び装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE19830539.7 1998-07-08
DE19830539 1998-07-08

Publications (2)

Publication Number Publication Date
WO2000003355A2 WO2000003355A2 (fr) 2000-01-20
WO2000003355A3 true WO2000003355A3 (fr) 2000-04-20

Family

ID=7873363

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/DE1999/001952 Ceased WO2000003355A2 (fr) 1998-07-08 1999-07-01 Reseau neuronal, et procede et dispositif pour l'entrainement d'un reseau neuronal

Country Status (3)

Country Link
EP (1) EP1093639A2 (fr)
JP (1) JP2002520719A (fr)
WO (1) WO2000003355A2 (fr)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB9920950D0 (en) 1999-09-06 1999-11-10 Ici Ltd Apparatus and method for reducing residual solvent levels
CN102663495B (zh) * 2012-02-22 2014-12-10 天津大学 一种用于非线性器件建模的神经网络数据生成方法
JP6164639B2 (ja) * 2013-05-23 2017-07-19 国立研究開発法人情報通信研究機構 ディープ・ニューラルネットワークの学習方法、及びコンピュータプログラム
DE102015226656B4 (de) 2015-12-23 2019-10-10 Siemens Aktiengesellschaft Verfahren und Softsensor zum Ermitteln einer Leistung eines Energieerzeugers
DE102018206108A1 (de) * 2018-04-20 2019-10-24 Zf Friedrichshafen Ag Generieren von Validierungsdaten mit generativen kontradiktorischen Netzwerken
DE102019204136A1 (de) * 2019-03-26 2020-10-01 Robert Bosch Gmbh Verfahren und Vorrichtung für Training und Herstellung eines künstlichen neuronalen Netzes
EP3716238B1 (fr) * 2019-03-27 2023-03-15 Siemens Aktiengesellschaft Procédé de détermination d'une stratégie d'évacuation pour l'évacuation d'un bâtiment

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0727748A1 (fr) * 1995-02-17 1996-08-21 BODAMER, Edgar Méthode et dispositif pour apprentissage non-supervisé multicouche en utilisant une hiérarchie de réseaux neuronaux

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0727748A1 (fr) * 1995-02-17 1996-08-21 BODAMER, Edgar Méthode et dispositif pour apprentissage non-supervisé multicouche en utilisant une hiérarchie de réseaux neuronaux

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
BAO-LIANG LU ET AL: "A MULTI-SIEVING NEURAL NETWORK ARCHITECTURE THAT DECOMPOSES LEARNING TASKS AUTOMATICALLY", PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS (ICNN),US,NEW YORK, IEEE, 27 June 1994 (1994-06-27) - 29 June 1994 (1994-06-29), pages 1319 - 1324, XP000503845, ISBN: 0-7803-1902-8 *
KAJIRO WATANABE ET AL: "INCIPIENT DIAGNOSIS OF MULTIPLE FAULTS IN CHEMICAL PROCESSES VIA HIERARCHICAL ARTIFICIAL NEURAL NETWORK", PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INDUSTRIAL ELECTRONICS,CONTROL AND INSTRUMENTATION (IECON),US,NEW YORK, IEEE, vol. CONF. 17, 28 October 1991 (1991-10-28) - 1 November 1991 (1991-11-01), pages 1500 - 1505, XP000313482, ISBN: 0-87942-688-8 *
SUNG JOO PARK ET AL: "A HIERARCHICAL NEURAL NETWORK APPROACH TO INTELLIGENT TRAFFIC CONTROL", PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS (ICNN),US,NEW YORK, IEEE, 27 June 1994 (1994-06-27), pages 3358 - 3362, XP000532726, ISBN: 0-7803-1902-8 *
WU Q H ET AL: "A NEURAL NETWORK REGULATOR FOR TURBOGENERATORS", IEEE TRANSACTIONS ON NEURAL NETWORKS,US,IEEE INC, NEW YORK, vol. 3, no. 1, 1 January 1992 (1992-01-01), pages 95 - 100, XP000262190, ISSN: 1045-9227 *

Also Published As

Publication number Publication date
JP2002520719A (ja) 2002-07-09
EP1093639A2 (fr) 2001-04-25
WO2000003355A2 (fr) 2000-01-20

Similar Documents

Publication Publication Date Title
AU5422996A (en) Transverse-fold pop-up device, and blank and method therefor
GB2318439B (en) Device and method for representing handwriting, and an alphabet therefor
GB2304766B (en) Offshore well apparatus and method
ZA976375B (en) Exercise methods and apparatus.
AU2001263316A1 (en) Distributed biometric access control apparatus and method
AU2013499A (en) Glandular stimulator device and method
DK0802854T3 (da) Præget subsrat og fotoreceptorindretning, der indbefatter dette, og fremgangsmåde
IT1284150B1 (it) Dispositivo elettronico portatile e metodo per la sua alimentazione.
AU5266596A (en) Method for signature and session key generation
EP0808028A4 (fr) Procede de modulation d'impulsions, modulateur d'impulsions et demodulateur d'impulsions
AU2953695A (en) Animal control, training apparatus and method of use
AUPN552595A0 (en) Wood corer device and method
EP0680174A3 (fr) Procédé et dispositif pour le contrÔle de communications.
AU6662598A (en) Novel down hole device and method
AU1549895A (en) Guitar feedback device and method
AU7106696A (en) Golf training apparatus and method
CA2353206A1 (fr) Appareil et methode de reconstruction de ligaments
AU6893496A (en) Method and device for drilling
AU6480696A (en) Quilting method and apparatus
WO2000003355A3 (fr) Reseau neuronal, et procede et dispositif pour l'entrainement d'un reseau neuronal
AU5061498A (en) Ph altering device and method
AUPN244495A0 (en) Sorting device and method
WO2001047110A3 (fr) Procede et dispositif destines a modifier une caracteristique d'un appareil
EP0659570A3 (fr) Appareil pour la production de figures et procédé pour la production de figures.
EP0621538A3 (fr) Méthode et dispositif de sortie.

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): JP US

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
AK Designated states

Kind code of ref document: A3

Designated state(s): JP US

AL Designated countries for regional patents

Kind code of ref document: A3

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE

WWE Wipo information: entry into national phase

Ref document number: 1999942765

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 09743429

Country of ref document: US

ENP Entry into the national phase

Ref country code: JP

Ref document number: 2000 559532

Kind code of ref document: A

Format of ref document f/p: F

WWP Wipo information: published in national office

Ref document number: 1999942765

Country of ref document: EP

WWW Wipo information: withdrawn in national office

Ref document number: 1999942765

Country of ref document: EP