[go: up one dir, main page]

WO2006005665A3 - Verfahren zur reaktion auf kontextänderungen mit einem neuronalen netz und neuronales netz zur reaktion auf kontextänderungen - Google Patents

Verfahren zur reaktion auf kontextänderungen mit einem neuronalen netz und neuronales netz zur reaktion auf kontextänderungen Download PDF

Info

Publication number
WO2006005665A3
WO2006005665A3 PCT/EP2005/052859 EP2005052859W WO2006005665A3 WO 2006005665 A3 WO2006005665 A3 WO 2006005665A3 EP 2005052859 W EP2005052859 W EP 2005052859W WO 2006005665 A3 WO2006005665 A3 WO 2006005665A3
Authority
WO
WIPO (PCT)
Prior art keywords
neural network
context
reacting
changes
piece
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/EP2005/052859
Other languages
English (en)
French (fr)
Other versions
WO2006005665A2 (de
Inventor
Gustavo Deco
Martin Stetter
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
Publication of WO2006005665A2 publication Critical patent/WO2006005665A2/de
Publication of WO2006005665A3 publication Critical patent/WO2006005665A3/de
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
    • G06N3/04—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
    • G06N3/08—Learning methods
    • G06N3/092—Reinforcement 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)
  • Image Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Bei dem Verfahren zur Reaktion auf Kontextänderungen mit einem neuronalen Netz (1) werden einer Eingabeschicht (10) des neuronalen Netzes (1) Eingabeinformationen zugeführt. Weiterhin werden einer Ausgabeschicht (30) des neuronalen Netzes (1) Ausgabeinformationen entnommen. Ferner sind in dem neuronalen Netz (1) mehrere Modelle gespeichert, welche jeweils eine Abbildung der Eingabeinformationen auf die Ausgabeinformationen vorgeben. Hierbei kann jeweils nur ein Modell gleichzeitig aktiv sein. Es werden nun folgende Schritte wiederholt: Das neuronale Netz (1) bildet eine zugeführte Eingabeinformation (2) mit dem aktiven Modell auf eine Ausgabeinformation (3) ab. Diese wird anschließend der Ausgabeschicht (30) entnommen. Wenn die entnommene Ausgabeinformation (3) für die zugeführte Eingabeinformation (2) in einem aktuellen Kontext falsch ist, erhält das neuronale Netz (1) eine Falsch-Rückmeldung (4), woraufhin das neuronale Netz (1) ein anderes Modell aktiviert.
PCT/EP2005/052859 2004-07-09 2005-06-21 Verfahren zur reaktion auf kontextänderungen mit einem neuronalen netz und neuronales netz zur reaktion auf kontextänderungen Ceased WO2006005665A2 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102004033391 2004-07-09
DE102004033391.2 2004-07-09

Publications (2)

Publication Number Publication Date
WO2006005665A2 WO2006005665A2 (de) 2006-01-19
WO2006005665A3 true WO2006005665A3 (de) 2006-12-07

Family

ID=35448080

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2005/052859 Ceased WO2006005665A2 (de) 2004-07-09 2005-06-21 Verfahren zur reaktion auf kontextänderungen mit einem neuronalen netz und neuronales netz zur reaktion auf kontextänderungen

Country Status (1)

Country Link
WO (1) WO2006005665A2 (de)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7577099B1 (en) * 2006-04-06 2009-08-18 At&T Corp. Method and apparatus for fault localization in a network
DE102007014650B3 (de) * 2007-03-27 2008-06-12 Siemens Ag Verfahren zur rechnergestützten Verarbeitung von in einem Sensornetzwerk erfassten Messwerten

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5155801A (en) * 1990-10-09 1992-10-13 Hughes Aircraft Company Clustered neural networks
US5239594A (en) * 1991-02-12 1993-08-24 Mitsubishi Denki Kabushiki Kaisha Self-organizing pattern classification neural network system
EP0574951A2 (de) * 1992-06-18 1993-12-22 Seiko Epson Corporation Spracherkennungssystem
EP1073012A1 (de) * 1999-07-30 2001-01-31 Eidgenössische Technische Hochschule Zürich Verfahren und Schaltung für neuron-ähnliche Datenverarbeitung
EP1327959A2 (de) * 2002-01-11 2003-07-16 EADS Deutschland GmbH Neuronales Netz zur Modellierung eines physikalischen Systems sowie Verfahren zur Bildung eines solchen neuronalen Netzes

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5155801A (en) * 1990-10-09 1992-10-13 Hughes Aircraft Company Clustered neural networks
US5239594A (en) * 1991-02-12 1993-08-24 Mitsubishi Denki Kabushiki Kaisha Self-organizing pattern classification neural network system
EP0574951A2 (de) * 1992-06-18 1993-12-22 Seiko Epson Corporation Spracherkennungssystem
EP1073012A1 (de) * 1999-07-30 2001-01-31 Eidgenössische Technische Hochschule Zürich Verfahren und Schaltung für neuron-ähnliche Datenverarbeitung
EP1327959A2 (de) * 2002-01-11 2003-07-16 EADS Deutschland GmbH Neuronales Netz zur Modellierung eines physikalischen Systems sowie Verfahren zur Bildung eines solchen neuronalen Netzes

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
SZABO MIRUNA ET AL: "COORPERATION AND BIASED COMPETITION MODEL CAN EXPLAIN ATTENTIANAL FILTERING IN THE PREFRONTAL CORTEX", EUROPEAN JOURNAL OF NEUROSCIENCE, OXFORD UNIVERSITY PRESS, GB, vol. 19, no. 6, April 2004 (2004-04-01), pages 1969 - 1977, XP008069137, ISSN: 0953-816X *

Also Published As

Publication number Publication date
WO2006005665A2 (de) 2006-01-19

Similar Documents

Publication Publication Date Title
WO2024226801A3 (en) Systems, methods, kits, and apparatuses for generative artificial intelligence, graphical neural networks, transformer models, and converging technology stacks in value chain networks
WO2005034180A3 (en) System and method for on-tool semiconductor simulation
WO2006056972A3 (en) Method and apparatus for speaker spotting
GB2424056A (en) Apparatus for providing haptic feedback
GB2438555A (en) Method and system for product design
WO2005006140A3 (en) Methods to attribute conversions for online advertisement campaigns
WO2004013808A3 (en) Methods for single qubit gate teleportation
WO2006111401A3 (en) A technique for platform-independent service modeling
SG113602A1 (en) Method of predicting and minimizing model opc deviation due to mix/match of exposure tools using a calibrated eigen decomposition model
WO2007022781A3 (en) Selecting virtual brick models
WO2006135417A3 (en) System, method and computer program product for developing a system-of-systems architecture model
WO2004104742A3 (en) System and method for generating a report using a knowledge base
EA200600036A1 (ru) Способ прогнозирования и автоматизированного проектирования одиночной скважины и вычислительная система для его осуществления
TW200617708A (en) System and method for optimizing animal production
SG126058A1 (en) System and method for applying development patterns for component based applications
WO2004031894A3 (en) Selective deployment of software extensions within an enterprise modeling environment
WO2005070115A3 (en) Proprietary protocol for voip based features
WO2005094493A3 (en) Apparatus and method for improving reliability of collected sensor data over a network
WO2008004125A3 (en) Business model generator
WO2005015352A3 (en) System and method for online expense management and validation
WO2006081084A3 (en) Remote component and connection architecture
WO2006060113A3 (en) Method and apparatus for providing push-to-talk based execution of an emergency plan
Ghorbani et al. Near-time-optimal motion control for flexible-link systems using absolute nodal coordinates formulation
WO2005044622A3 (en) Method and apparatus for loss of control inhibitor systems
WO2002079917A3 (en) Versioning method for business process models

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KM KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NG NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): BW GH GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
NENP Non-entry into the national phase

Ref country code: DE

WWW Wipo information: withdrawn in national office

Country of ref document: DE

122 Ep: pct application non-entry in european phase