WO2007020456A3 - Neural network method and apparatus - Google Patents

Neural network method and apparatus Download PDF

Info

Publication number
WO2007020456A3
WO2007020456A3 PCT/GB2006/003093 GB2006003093W WO2007020456A3 WO 2007020456 A3 WO2007020456 A3 WO 2007020456A3 GB 2006003093 W GB2006003093 W GB 2006003093W WO 2007020456 A3 WO2007020456 A3 WO 2007020456A3
Authority
WO
WIPO (PCT)
Prior art keywords
neural network
operative
adopt
received
training data
Prior art date
Application number
PCT/GB2006/003093
Other languages
French (fr)
Other versions
WO2007020456A2 (en
Inventor
Heige Nareid
Original Assignee
Axeon Ltd
Heige Nareid
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
Priority claimed from GB0517033A external-priority patent/GB0517033D0/en
Priority claimed from GB0517009A external-priority patent/GB0517009D0/en
Application filed by Axeon Ltd, Heige Nareid filed Critical Axeon Ltd
Publication of WO2007020456A2 publication Critical patent/WO2007020456A2/en
Publication of WO2007020456A3 publication Critical patent/WO2007020456A3/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
    • F02D—CONTROLLING COMBUSTION ENGINES
    • F02D41/00—Electrical control of supply of combustible mixture or its constituents
    • F02D41/02—Circuit arrangements for generating control signals
    • F02D41/14—Introducing closed-loop corrections
    • F02D41/1401—Introducing closed-loop corrections characterised by the control or regulation method
    • F02D41/1405—Neural network control
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
    • F02D—CONTROLLING COMBUSTION ENGINES
    • F02D41/00—Electrical control of supply of combustible mixture or its constituents
    • F02D41/02—Circuit arrangements for generating control signals
    • F02D41/18—Circuit arrangements for generating control signals by measuring intake air flow

Abstract

The invention relates to a method of training a neural network apparatus (10). The neural network apparatus (10) comprises a neural network (12), which has a plurality of neurons (14) and at least one function processor (16) operable to receive an output (28) from at least one of the plurality of neurons and to provide a processor output (40) in dependence upon the received output . The method comprises receiving a first set of training data in the neural network, the neural network being operative to adopt a trained response characteristic in dependence upon the received first set of training data. A second set of training data is received in the function processor, the function processor being operative to adopt a trained response characteristic in dependence upon the received second set of training data. The function processor is operative to adopt its trained response characteristic after the neural network is operative to adopt its trained response characteristic.
PCT/GB2006/003093 2005-08-19 2006-08-18 Neural network method and apparatus WO2007020456A2 (en)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
GB0517033A GB0517033D0 (en) 2005-08-19 2005-08-19 Method and apparatus for data classification and change detection
GB0517033.7 2005-08-19
GB0517009.7 2005-08-19
GB0517009A GB0517009D0 (en) 2005-08-19 2005-08-19 Apparatus and method for function estimation

Publications (2)

Publication Number Publication Date
WO2007020456A2 WO2007020456A2 (en) 2007-02-22
WO2007020456A3 true WO2007020456A3 (en) 2007-08-16

Family

ID=37654791

Family Applications (2)

Application Number Title Priority Date Filing Date
PCT/GB2006/003093 WO2007020456A2 (en) 2005-08-19 2006-08-18 Neural network method and apparatus
PCT/GB2006/003111 WO2007020466A2 (en) 2005-08-19 2006-08-18 Data classification apparatus and method

Family Applications After (1)

Application Number Title Priority Date Filing Date
PCT/GB2006/003111 WO2007020466A2 (en) 2005-08-19 2006-08-18 Data classification apparatus and method

Country Status (1)

Country Link
WO (2) WO2007020456A2 (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2085594B1 (en) 2008-01-29 2010-06-30 Honda Motor Co., Ltd. Control system for internal combustion engine
EP2085593B1 (en) * 2008-01-29 2010-06-30 Honda Motor Co., Ltd. Control system for internal combustion engine
GB2495875B (en) 2010-07-06 2017-08-02 Bae Systems Plc Assisting vehicle guidance over terrain
WO2017058133A1 (en) * 2015-09-28 2017-04-06 General Electric Company Apparatus and methods for allocating and indicating engine control authority
US10260407B2 (en) 2016-02-03 2019-04-16 Cummins Inc. Gas quality virtual sensor for an internal combustion engine
WO2019084556A1 (en) * 2017-10-27 2019-05-02 Google Llc Increasing security of neural networks by discretizing neural network inputs
GB201719587D0 (en) * 2017-11-24 2018-01-10 Sage Global Services Ltd Method and apparatus for determining an association
CN111832342A (en) * 2019-04-16 2020-10-27 阿里巴巴集团控股有限公司 Neural network, training and using method, device, electronic equipment and medium
CN115879350A (en) * 2023-02-07 2023-03-31 华中科技大学 Aircraft resistance coefficient prediction method based on sequential sampling

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0441522A2 (en) * 1990-02-09 1991-08-14 Hitachi, Ltd. Control device for an automobile
US5303330A (en) * 1991-06-03 1994-04-12 Bell Communications Research, Inc. Hybrid multi-layer neural networks
EP0877309A1 (en) * 1997-05-07 1998-11-11 Ford Global Technologies, Inc. Virtual vehicle sensors based on neural networks trained using data generated by simulation models
WO2000045333A1 (en) * 1999-02-01 2000-08-03 Axeon Limited Neural processing element for use in a neural network
EP1340888A2 (en) * 2002-03-01 2003-09-03 Axeon Limited Control of a mechanical actuator using a modular map processor

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6292738B1 (en) * 2000-01-19 2001-09-18 Ford Global Tech., Inc. Method for adaptive detection of engine misfire
KR100442835B1 (en) * 2002-08-13 2004-08-02 삼성전자주식회사 Face recognition method using artificial neural network, and the apparatus using thereof

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0441522A2 (en) * 1990-02-09 1991-08-14 Hitachi, Ltd. Control device for an automobile
EP0441522B1 (en) * 1990-02-09 1994-03-30 Hitachi, Ltd. Control device for an automobile
US5303330A (en) * 1991-06-03 1994-04-12 Bell Communications Research, Inc. Hybrid multi-layer neural networks
EP0877309A1 (en) * 1997-05-07 1998-11-11 Ford Global Technologies, Inc. Virtual vehicle sensors based on neural networks trained using data generated by simulation models
EP0877309B1 (en) * 1997-05-07 2000-06-21 Ford Global Technologies, Inc. Virtual vehicle sensors based on neural networks trained using data generated by simulation models
WO2000045333A1 (en) * 1999-02-01 2000-08-03 Axeon Limited Neural processing element for use in a neural network
EP1340888A2 (en) * 2002-03-01 2003-09-03 Axeon Limited Control of a mechanical actuator using a modular map processor

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
HELGE NAREID AND NEIL LIGHTOWLER: "Detection of Engine Misfire Events Using An Artificial Neural Network", SAE TECHNICAL PAPERS, no. 2004-01-1363, 2004, XP008080040 *
HELGE NAREID ET AL: "A NEURAL NETWORK BASED METHODOLOGY FOR VIRTUAL SENSOR DEVELOPMENT", SOCIETY OF AUTOMOTIVE ENGINEERS PUBLICATIONS, no. 2005-01-0045, April 2005 (2005-04-01), pages 205 - 208, XP008080036 *
PAUL NEIL, SIMON P. BREWERTON: "Rapid Prototyping of Machine Learning Systems", SAE TECHNICAL PAPER, no. 2005-01-0038, April 2005 (2005-04-01), XP008080038 *

Also Published As

Publication number Publication date
WO2007020466A3 (en) 2007-11-01
WO2007020456A2 (en) 2007-02-22
WO2007020466A2 (en) 2007-02-22

Similar Documents

Publication Publication Date Title
WO2007020456A3 (en) Neural network method and apparatus
WO2004061820A3 (en) Method and apparatus for selective distributed speech recognition
WO2005017690A3 (en) Systems and methods for creation and use of an adaptive reference model
WO2003075196A3 (en) Expertise modelling
WO2002095534A3 (en) Methods for feature selection in a learning machine
WO2003025858A3 (en) Method for identifying and quantifying characteristics of seeds and other small objects
WO2003090164A3 (en) System and method for providing inferencing services
WO2004055778A3 (en) Method and apparatus for selective speech recognition
EP1197902A3 (en) Information processing apparatus, system and method, and recording medium
WO2006019389A3 (en) System and method for ordering haptic effects
WO2005066868A3 (en) Sleep and environment control method and system
WO2005098788A3 (en) System and method for assessment design
WO2005086068A3 (en) Methods and systems for predicting occurrence of an event
AU2003253405A1 (en) Method, data processing device and computer program product for processing data
WO2006026688A3 (en) Method and apparatus for classifying an object
WO2007050622A3 (en) Weighted pattern learning for neural networks
WO2005065147A3 (en) System and method for mapping instructions associated with haptic feedback
WO2005074487A3 (en) Method and apparatus for information notification
WO2005114504A3 (en) Method and apparatus for executing event driven simulations
WO2005008412A3 (en) Shared input key method and apparatus
WO2002095714A3 (en) Method and device for controlling the posture or movement of a person
WO2007022428A3 (en) Systems, methods, and apparatus for table construction and use in image processing
EP1335560A3 (en) Server computer protection apparatus and method for controlling data transfer by the same
WO2006122106A3 (en) Processing information from selected sources via a single website
EP1439488A3 (en) Image processing system, method and program

Legal Events

Date Code Title Description
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

122 Ep: pct application non-entry in european phase

Ref document number: 06779165

Country of ref document: EP

Kind code of ref document: A2