Context propagation based on membership feedback

Kohei Inoue, Kiichi Urahama

Research output: Contribution to journalArticle

Abstract

The authors discuss a simple model for pattern discrimination incorporating temporal or spatial context by feedback of the membership values output at the high-rank winner-take-all (WTA) neurons to the lower-rank pattern selection response neurons. They propose a teacherless training method based on maximum likelihood. First, for the temporal context, they study examples with the feedback of discrimination effect of a first moment to the next moment, and demonstrate that clustering is performed by proximity of presentation moments rather than by the pattern similarity. Next, for the spatial context, they show that a similar pattern recognition method can be applied to spatial smoothing of image patterns.

Original languageEnglish
Pages (from-to)45-52
Number of pages8
JournalSystems and Computers in Japan
Volume32
Issue number1
DOIs
Publication statusPublished - Jan 1 2001

Fingerprint

Neurons
Propagation
Feedback
Moment
Maximum likelihood
Discrimination
Pattern recognition
Neuron
Winner-take-all
Proximity
Pattern Recognition
Maximum Likelihood
Smoothing
Clustering
Context
Output
Demonstrate
Model

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Information Systems
  • Hardware and Architecture
  • Computational Theory and Mathematics

Cite this

Context propagation based on membership feedback. / Inoue, Kohei; Urahama, Kiichi.

In: Systems and Computers in Japan, Vol. 32, No. 1, 01.01.2001, p. 45-52.

Research output: Contribution to journalArticle

Inoue, Kohei ; Urahama, Kiichi. / Context propagation based on membership feedback. In: Systems and Computers in Japan. 2001 ; Vol. 32, No. 1. pp. 45-52.
@article{d17b661ad19448b291f01d8a8c66d465,
title = "Context propagation based on membership feedback",
abstract = "The authors discuss a simple model for pattern discrimination incorporating temporal or spatial context by feedback of the membership values output at the high-rank winner-take-all (WTA) neurons to the lower-rank pattern selection response neurons. They propose a teacherless training method based on maximum likelihood. First, for the temporal context, they study examples with the feedback of discrimination effect of a first moment to the next moment, and demonstrate that clustering is performed by proximity of presentation moments rather than by the pattern similarity. Next, for the spatial context, they show that a similar pattern recognition method can be applied to spatial smoothing of image patterns.",
author = "Kohei Inoue and Kiichi Urahama",
year = "2001",
month = "1",
day = "1",
doi = "10.1002/1520-684X(200101)32:1<45::AID-SCJ6>3.0.CO;2-K",
language = "English",
volume = "32",
pages = "45--52",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "1",

}

TY - JOUR

T1 - Context propagation based on membership feedback

AU - Inoue, Kohei

AU - Urahama, Kiichi

PY - 2001/1/1

Y1 - 2001/1/1

N2 - The authors discuss a simple model for pattern discrimination incorporating temporal or spatial context by feedback of the membership values output at the high-rank winner-take-all (WTA) neurons to the lower-rank pattern selection response neurons. They propose a teacherless training method based on maximum likelihood. First, for the temporal context, they study examples with the feedback of discrimination effect of a first moment to the next moment, and demonstrate that clustering is performed by proximity of presentation moments rather than by the pattern similarity. Next, for the spatial context, they show that a similar pattern recognition method can be applied to spatial smoothing of image patterns.

AB - The authors discuss a simple model for pattern discrimination incorporating temporal or spatial context by feedback of the membership values output at the high-rank winner-take-all (WTA) neurons to the lower-rank pattern selection response neurons. They propose a teacherless training method based on maximum likelihood. First, for the temporal context, they study examples with the feedback of discrimination effect of a first moment to the next moment, and demonstrate that clustering is performed by proximity of presentation moments rather than by the pattern similarity. Next, for the spatial context, they show that a similar pattern recognition method can be applied to spatial smoothing of image patterns.

UR - http://www.scopus.com/inward/record.url?scp=0035148245&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035148245&partnerID=8YFLogxK

U2 - 10.1002/1520-684X(200101)32:1<45::AID-SCJ6>3.0.CO;2-K

DO - 10.1002/1520-684X(200101)32:1<45::AID-SCJ6>3.0.CO;2-K

M3 - Article

AN - SCOPUS:0035148245

VL - 32

SP - 45

EP - 52

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 1

ER -