DE69333247D1 - Trainingsverfahren und Gerät zur Erzeugung eines neues Neurons - Google Patents

Trainingsverfahren und Gerät zur Erzeugung eines neues Neurons

Info

Publication number
DE69333247D1
DE69333247D1 DE69333247T DE69333247T DE69333247D1 DE 69333247 D1 DE69333247 D1 DE 69333247D1 DE 69333247 T DE69333247 T DE 69333247T DE 69333247 T DE69333247 T DE 69333247T DE 69333247 D1 DE69333247 D1 DE 69333247D1
Authority
DE
Germany
Prior art keywords
neuron
generating
new neuron
training method
existing
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
DE69333247T
Other languages
English (en)
Other versions
DE69333247T2 (de
Inventor
Michael C Moed
Chih-Ping Lee
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.)
United Parcel Service of America Inc
United Parcel Service Inc
Original Assignee
United Parcel Service of America Inc
United Parcel Service Inc
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 United Parcel Service of America Inc, United Parcel Service Inc filed Critical United Parcel Service of America Inc
Application granted granted Critical
Publication of DE69333247D1 publication Critical patent/DE69333247D1/de
Publication of DE69333247T2 publication Critical patent/DE69333247T2/de
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

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
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
    • G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24143—Distances to neighbourhood prototypes, e.g. restricted Coulomb energy networks [RCEN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/19—Recognition using electronic means
    • G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G06V30/19107—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/19—Recognition using electronic means
    • G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G06V30/19173—Classification techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Image Analysis (AREA)
  • Character Discrimination (AREA)
  • Electrotherapy Devices (AREA)
  • Finger-Pressure Massage (AREA)
  • Cable Transmission Systems, Equalization Of Radio And Reduction Of Echo (AREA)
  • Input From Keyboards Or The Like (AREA)
  • Electrophonic Musical Instruments (AREA)
DE69333247T 1992-06-19 1993-06-18 Trainingsverfahren und Gerät zur Erzeugung eines neues Neurons Expired - Lifetime DE69333247T2 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US07/901,429 US5438629A (en) 1992-06-19 1992-06-19 Method and apparatus for input classification using non-spherical neurons
US901429 1992-06-19

Publications (2)

Publication Number Publication Date
DE69333247D1 true DE69333247D1 (de) 2003-11-13
DE69333247T2 DE69333247T2 (de) 2004-08-05

Family

ID=25414169

Family Applications (3)

Application Number Title Priority Date Filing Date
DE69333215T Expired - Lifetime DE69333215T2 (de) 1992-06-19 1993-06-18 Trainingsverfahren und Gerät zur Einstellung eines Neurons
DE69331867T Expired - Lifetime DE69331867T2 (de) 1992-06-19 1993-06-18 Verfahren und Vorrichtung zur Eingabeklassifizierung mit nichtkugeligen Neuronen
DE69333247T Expired - Lifetime DE69333247T2 (de) 1992-06-19 1993-06-18 Trainingsverfahren und Gerät zur Erzeugung eines neues Neurons

Family Applications Before (2)

Application Number Title Priority Date Filing Date
DE69333215T Expired - Lifetime DE69333215T2 (de) 1992-06-19 1993-06-18 Trainingsverfahren und Gerät zur Einstellung eines Neurons
DE69331867T Expired - Lifetime DE69331867T2 (de) 1992-06-19 1993-06-18 Verfahren und Vorrichtung zur Eingabeklassifizierung mit nichtkugeligen Neuronen

Country Status (6)

Country Link
US (1) US5438629A (de)
EP (3) EP1197913B1 (de)
JP (1) JP2925434B2 (de)
AT (2) ATE250250T1 (de)
DE (3) DE69333215T2 (de)
ES (2) ES2207584T3 (de)

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0602717B1 (de) * 1992-12-16 1997-10-01 Laboratoires D'electronique Philips S.A.S. Neuronalanlage und -Bauverfahren
EP0612035B1 (de) * 1993-02-19 2002-01-30 International Business Machines Corporation Neuronales Netz zum Vergleich von Merkmalen von Bildmustern
US5835901A (en) * 1994-01-25 1998-11-10 Martin Marietta Corporation Perceptive system including a neural network
US6466926B1 (en) * 1996-03-06 2002-10-15 Hewlett-Packard Company Method for optimizing a recognition dictionary to distinguish between patterns that are difficult to distinguish
US6049793A (en) * 1996-11-15 2000-04-11 Tomita; Kenichi System for building an artificial neural network
US6336109B2 (en) * 1997-04-15 2002-01-01 Cerebrus Solutions Limited Method and apparatus for inducing rules from data classifiers
US7324926B2 (en) * 1999-04-09 2008-01-29 Whitehead Institute For Biomedical Research Methods for predicting chemosensitivity or chemoresistance
US6647341B1 (en) * 1999-04-09 2003-11-11 Whitehead Institute For Biomedical Research Methods for classifying samples and ascertaining previously unknown classes
US6694301B1 (en) * 2000-03-31 2004-02-17 Microsoft Corporation Goal-oriented clustering
US7062498B2 (en) * 2001-11-02 2006-06-13 Thomson Legal Regulatory Global Ag Systems, methods, and software for classifying text from judicial opinions and other documents
KR100473598B1 (ko) * 2002-11-04 2005-03-11 삼성전자주식회사 가려진 얼굴영상을 판단하는 시스템 및 방법
MY138544A (en) 2003-06-26 2009-06-30 Neuramatix Sdn Bhd Neural networks with learning and expression capability
AR047363A1 (es) * 2003-12-31 2006-01-18 Thomson Global Resources Ag Sistemas, metodos, software e interfases para la integracion de jurisprudencia en presentaciones judiciales, escritos judiciales y/u otros documentos de apoyo a las presentaciones judiciales
CN108733003B (zh) * 2017-04-20 2020-11-13 南京理工大学 基于kmeans聚类算法的回转类零件工序工时预测方法及***
SG11202002865TA (en) 2017-09-28 2020-04-29 Agency Science Tech & Res Self-assessing deep representational units
CN108631817B (zh) * 2018-05-10 2020-05-19 东北大学 一种基于时频分析和径向神经网络进行跳频信号频段预测的方法

Family Cites Families (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5035379B1 (de) * 1970-05-25 1975-11-15
US3950733A (en) * 1974-06-06 1976-04-13 Nestor Associates Information processing system
US4044243A (en) * 1976-07-23 1977-08-23 Nestor Associates Information processing system
US4326259A (en) * 1980-03-27 1982-04-20 Nestor Associates Self organizing general pattern class separator and identifier
JPH0638276B2 (ja) * 1983-12-14 1994-05-18 株式会社日立製作所 パターン識別装置
US4599693A (en) * 1984-01-16 1986-07-08 Itt Corporation Probabilistic learning system
US5054093A (en) * 1985-09-12 1991-10-01 Cooper Leon N Parallel, multi-unit, adaptive, nonlinear pattern class separator and identifier
JPS62133589A (ja) * 1985-12-05 1987-06-16 Mitsubishi Heavy Ind Ltd パタ−ン記憶識別装置
JPH0233687A (ja) * 1988-07-22 1990-02-02 Nec Corp マルチフォント文字認識用ニューラルネットワーク学習方法
JPH0735591B2 (ja) * 1988-07-27 1995-04-19 三菱重工業株式会社 酸洗前処理装置
JPH0242392A (ja) * 1988-08-03 1990-02-13 Central Res Inst Of Electric Power Ind 原子炉容器の耐震支持構造
US5010512A (en) * 1989-01-12 1991-04-23 International Business Machines Corp. Neural network having an associative memory that learns by example
US4954963A (en) * 1989-03-02 1990-09-04 Texas Instruments Incorporated Neural network and system
JPH0738186B2 (ja) * 1989-03-13 1995-04-26 シャープ株式会社 自己拡張形ニユーラル・ネットワーク
JPH0821065B2 (ja) * 1989-03-13 1996-03-04 シャープ株式会社 文字認識装置
JP2680419B2 (ja) * 1989-05-15 1997-11-19 株式会社東芝 文字認識装置
JP2940933B2 (ja) * 1989-05-20 1999-08-25 株式会社リコー パターン認識方式
US5086479A (en) * 1989-06-30 1992-02-04 Hitachi, Ltd. Information processing system using neural network learning function
US5067164A (en) * 1989-11-30 1991-11-19 At&T Bell Laboratories Hierarchical constrained automatic learning neural network for character recognition
FR2658337A1 (fr) * 1990-02-09 1991-08-16 Philips Electronique Lab Procede d'apprentissage d'un reseau de neurones hierarchise et reseau de neurones hierarchise.
JPH07113943B2 (ja) * 1990-04-16 1995-12-06 シャープ株式会社 ニューラルネットワークの学習方法
US5245697A (en) * 1990-04-24 1993-09-14 Kabushiki Kaisha Toshiba Neural network processing apparatus for identifying an unknown image pattern as one of a plurality of instruction image patterns
US5058180A (en) * 1990-04-30 1991-10-15 National Semiconductor Corporation Neural network apparatus and method for pattern recognition
US5181171A (en) * 1990-09-20 1993-01-19 Atlantic Richfield Company Adaptive network for automated first break picking of seismic refraction events and method of operating the same
US5265192A (en) * 1990-09-20 1993-11-23 Atlantic Richfield Company Method for the automated editing of seismic traces using an adaptive network
US5214744A (en) * 1990-12-14 1993-05-25 Westinghouse Electric Corp. Method and apparatus for automatically identifying targets in sonar images
DE4100500A1 (de) * 1991-01-10 1992-07-16 Bodenseewerk Geraetetech Signalverarbeitungsanordnung zur klassifizierung von objekten aufgrund der signale von sensoren
US5214715A (en) * 1991-01-31 1993-05-25 Trustees Of Boston University Predictive self-organizing neural network
US5239594A (en) * 1991-02-12 1993-08-24 Mitsubishi Denki Kabushiki Kaisha Self-organizing pattern classification neural network system
US5260871A (en) * 1991-07-31 1993-11-09 Mayo Foundation For Medical Education And Research Method and apparatus for diagnosis of breast tumors

Also Published As

Publication number Publication date
EP0574936A3 (en) 1994-07-20
JPH06176160A (ja) 1994-06-24
EP1197913B1 (de) 2003-09-17
EP0574936B1 (de) 2002-05-02
DE69333215T2 (de) 2004-07-01
ES2208511T3 (es) 2004-06-16
DE69331867T2 (de) 2002-11-14
ATE251781T1 (de) 2003-10-15
ATE250250T1 (de) 2003-10-15
EP1197914B1 (de) 2003-10-08
JP2925434B2 (ja) 1999-07-28
US5438629A (en) 1995-08-01
EP0574936A2 (de) 1993-12-22
DE69333247T2 (de) 2004-08-05
ES2207584T3 (es) 2004-06-01
DE69333215D1 (de) 2003-10-23
EP1197914A1 (de) 2002-04-17
EP1197913A1 (de) 2002-04-17
DE69331867D1 (de) 2002-06-06

Similar Documents

Publication Publication Date Title
ATE251781T1 (de) Trainingsverfahren und gerät zur erzeugung eines neues neurons
NO984502L (no) Tale-prosessering
ATE184406T1 (de) Verfahren und vorrichtung in bezug auf die herstellung eines dreidimensionalen körpers, verwendbar in einem menschenkörper
ATE386989T1 (de) Verfahren und vorrichtung zum dekodieren handschriftlicher zeichen
DE69521659D1 (de) Verfahren und anordnung mit einem artikulator sowie einer datenverarbeitungsanlage
DE59605506D1 (de) Intelligentes rechner-leitsystem
DE69818217D1 (de) Methode und Vorrichtung zum Simulieren von Kunstmalerei oder künstlerischem Zeichnen
ATE210311T1 (de) Verfahren und -vorrichtung zur erzeugung eines mensch/maschine-dialogs mit bedienereingriff
NO951809L (no) Generelt analysesystem
ITRM910076A0 (it) Architettura per rete neuronica fisicamente inseribile nel processo di apprendimento.
DE69131020D1 (de) Gerät geeignet zur objekt-hintergrund-abtrennung
DE69942656D1 (de) Datenverarbeitungsanlage und -verfahren
DE69230139D1 (de) Anordnung zur signalverarbeitung
ATE166507T1 (de) Binärdateneinschreibungsverfahren, insbesondere optisches, und vorrichtung zur durchführung dieses verfahrens
ATE190422T1 (de) Gerät zur verwendung als lernspielzeug
DE69029538D1 (de) Lernverfahren, neuronales Netz und Rechner zur Simulation eines solchen neuronalen Netzes
DE69030812D1 (de) Verfahren und gerät um einen prozess zu steuern mit hilfe eines trainierten parallel verteilten verarbeitungsnetzwerkes
ATE188557T1 (de) Verfahren und anordung zur erzeugung von summeinformation-/rundungskontrolle-signal
KR910012982A (ko) 데이터 처리장치를 위한 특정데이터 선택방법
DE69819543D1 (de) Verfahren und gerät zur bearbeitung einer anfrage gemäss einer booleanregel
ATE139635T1 (de) Verfahren zum entwurf eines neuronalen netzes und danach erhaltenes neuronales netz
Nielsen The application of AI techniques to model maintenance.
Nor et al. Artificial Neural Network
Krejci Physical training as the factor of socialization on the pupil at the elementary school.
JPS6467603A (en) Intelligent type controller

Legal Events

Date Code Title Description
8364 No opposition during term of opposition