GB2253295A - Pattern recognition - Google Patents

Pattern recognition

Info

Publication number
GB2253295A
GB2253295A GB9127502A GB9127502A GB2253295A GB 2253295 A GB2253295 A GB 2253295A GB 9127502 A GB9127502 A GB 9127502A GB 9127502 A GB9127502 A GB 9127502A GB 2253295 A GB2253295 A GB 2253295A
Authority
GB
United Kingdom
Prior art keywords
weight values
pattern recognition
training
quantised
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.)
Granted
Application number
GB9127502A
Other versions
GB2253295B (en
GB9127502D0 (en
Inventor
Philip Charles Woodland
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.)
British Telecommunications PLC
Original Assignee
British Telecommunications PLC
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 British Telecommunications PLC filed Critical British Telecommunications PLC
Publication of GB9127502D0 publication Critical patent/GB9127502D0/en
Publication of GB2253295A publication Critical patent/GB2253295A/en
Application granted granted Critical
Publication of GB2253295B publication Critical patent/GB2253295B/en
Anticipated expiration legal-status Critical
Expired - Fee Related 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • 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
    • G06F18/24317—Piecewise classification, i.e. whereby each classification requires several discriminant rules
    • 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
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/16—Speech classification or search using artificial neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Complex Calculations (AREA)
  • Image Analysis (AREA)

Abstract

A neural net is trained on training data, and the weight values are increased up to a predetermined maximum value M; any weight values which would otherwise exceed M are set equal to M. Useful for training multi-layer perceptrons for speech recognition; results in weight values which are more easily quantised hence give a more robust performance.
GB9127502A 1989-06-30 1991-12-20 Pattern recognition Expired - Fee Related GB2253295B (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
GB898915085A GB8915085D0 (en) 1989-06-30 1989-06-30 Pattern recognition

Publications (3)

Publication Number Publication Date
GB9127502D0 GB9127502D0 (en) 1992-03-11
GB2253295A true GB2253295A (en) 1992-09-02
GB2253295B GB2253295B (en) 1993-11-03

Family

ID=10659352

Family Applications (2)

Application Number Title Priority Date Filing Date
GB898915085A Pending GB8915085D0 (en) 1989-06-30 1989-06-30 Pattern recognition
GB9127502A Expired - Fee Related GB2253295B (en) 1989-06-30 1991-12-20 Pattern recognition

Family Applications Before (1)

Application Number Title Priority Date Filing Date
GB898915085A Pending GB8915085D0 (en) 1989-06-30 1989-06-30 Pattern recognition

Country Status (7)

Country Link
EP (1) EP0484344A1 (en)
JP (1) JPH04506424A (en)
CA (1) CA2063426A1 (en)
FI (1) FI916155A0 (en)
GB (2) GB8915085D0 (en)
HK (1) HK132896A (en)
WO (1) WO1991000591A1 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0683781B2 (en) * 1986-03-14 1994-10-26 住友化学工業株式会社 Method for producing flaky material
GB9116255D0 (en) * 1991-07-27 1991-09-11 Dodd Nigel A Apparatus and method for monitoring
US5621858A (en) * 1992-05-26 1997-04-15 Ricoh Corporation Neural network acoustic and visual speech recognition system training method and apparatus
DE4300159C2 (en) * 1993-01-07 1995-04-27 Lars Dipl Ing Knohl Procedure for the mutual mapping of feature spaces
US11106973B2 (en) 2016-03-16 2021-08-31 Hong Kong Applied Science and Technology Research Institute Company Limited Method and system for bit-depth reduction in artificial neural networks

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0327817B1 (en) * 1988-01-11 1996-08-28 Yozan Inc. Associative pattern conversion system and adaptation method thereof

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
IEEE EXPERT,vol.3,no.1,spring 1988,pages10-15:"Neural networks,part 2" *
IEEE International conference on neural networks,San Diego,24-27 July 1988,pages 365-372 *
Proceedings of the fall joint computer conference,San Francisco,9-11 December 1968,pages 1117-1124 *

Also Published As

Publication number Publication date
CA2063426A1 (en) 1990-12-31
GB2253295B (en) 1993-11-03
EP0484344A1 (en) 1992-05-13
GB9127502D0 (en) 1992-03-11
JPH04506424A (en) 1992-11-05
WO1991000591A1 (en) 1991-01-10
HK132896A (en) 1996-08-02
FI916155A0 (en) 1991-12-30
GB8915085D0 (en) 1989-09-20

Similar Documents

Publication Publication Date Title
EP0510632A3 (en) Speech recognition by neural network adapted to reference pattern learning
CA2228948A1 (en) Pattern recognition
DE68912397D1 (en) Speech recognition with speaker adaptation through learning process.
WO1999016052A3 (en) Speech recognition system for recognizing continuous and isolated speech
EP0043006A3 (en) Pattern recognition apparatus using prototype probability matching
CA2229025A1 (en) Incorporating invariances by preprocessing for kernel-based methods
WO1995024017A3 (en) A top down preprocessor for a machine vision system
EP0572335A3 (en) Feature classification using supervised statistical pattern recognition.
EP2040453A3 (en) A method of recognising content signals in a network of computing devices
EP0591921A3 (en) Learning and recognition machine.
EP0660276A3 (en) Neural network for bank note recognition and authentication.
EP0559415A3 (en) A pattern matching method, a pattern recognition apparatus and speech recognition apparatus
EP0640935A3 (en) Pattern recognition using a neural network.
RU92016491A (en) ARTIFICIAL NEURAL DEVICE
EP1863014A3 (en) Apparatuses and methods for learning and using a distance transition model
JPS64997A (en) Speech recognition system using vector quantization
GB2253295A (en) Pattern recognition
ES2139112T3 (en) SPEECH RECOGNITION BASED ON HMMS.
EP0586714A4 (en) Speech recognition apparatus using neural network, and learning method therefor
EP0574936A3 (en) Method and apparatus for input classification using non-spherical neurons
EP0305215A3 (en) Speech recognition
GB8919522D0 (en) A hand-written,on-line character recognition apparatus and method
FR2660463B1 (en) CHARACTER RECOGNITION DEVICE, CHARACTER EXTRACTION METHOD, AND SUCCESSIVE NUMBER RECOGNITION METHOD USING SUCH A DEVICE.
FR2682790B1 (en) METHOD AND DEVICE FOR READING A BAR CODE WITH RECOGNITION OF THE PRESENCE OF AN INFRARED MASK.
JPS5743280A (en) Circuit device for recognizing pattern by machine

Legal Events

Date Code Title Description
PCNP Patent ceased through non-payment of renewal fee

Effective date: 19970629