Quantitative object motion prediction by an ART2 and Madaline combined neural network

Qiuming Zhu, Ahmed Y. Tawfik

Research output: Contribution to journalArticle

Abstract

An ART2 and a Madaline combined neural network is applied to predicting object motions in dynamic environments. The ART2 network extracts a set of coherent patterns of the object motion by its self-organizing and unsupervised learning features. The identified patterns are directed to the Madaline network to generate a quantitative prediction of the future motion states. The method does not require any presumption of the mathematical models, and is applicable to a variety of situations.

Original languageEnglish (US)
Pages (from-to)19-21
Number of pages3
JournalNeural Processing Letters
Volume2
Issue number1
DOIs
StatePublished - Jan 1 1995

Fingerprint

Unsupervised learning
Mathematical models
Neural networks
Theoretical Models
Learning

ASJC Scopus subject areas

  • Software
  • Neuroscience(all)
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Quantitative object motion prediction by an ART2 and Madaline combined neural network. / Zhu, Qiuming; Tawfik, Ahmed Y.

In: Neural Processing Letters, Vol. 2, No. 1, 01.01.1995, p. 19-21.

Research output: Contribution to journalArticle

@article{420fdf99c1ce44d184ca80a1d6f5b05c,
title = "Quantitative object motion prediction by an ART2 and Madaline combined neural network",
abstract = "An ART2 and a Madaline combined neural network is applied to predicting object motions in dynamic environments. The ART2 network extracts a set of coherent patterns of the object motion by its self-organizing and unsupervised learning features. The identified patterns are directed to the Madaline network to generate a quantitative prediction of the future motion states. The method does not require any presumption of the mathematical models, and is applicable to a variety of situations.",
author = "Qiuming Zhu and Tawfik, {Ahmed Y.}",
year = "1995",
month = "1",
day = "1",
doi = "10.1007/BF02312378",
language = "English (US)",
volume = "2",
pages = "19--21",
journal = "Neural Processing Letters",
issn = "1370-4621",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Quantitative object motion prediction by an ART2 and Madaline combined neural network

AU - Zhu, Qiuming

AU - Tawfik, Ahmed Y.

PY - 1995/1/1

Y1 - 1995/1/1

N2 - An ART2 and a Madaline combined neural network is applied to predicting object motions in dynamic environments. The ART2 network extracts a set of coherent patterns of the object motion by its self-organizing and unsupervised learning features. The identified patterns are directed to the Madaline network to generate a quantitative prediction of the future motion states. The method does not require any presumption of the mathematical models, and is applicable to a variety of situations.

AB - An ART2 and a Madaline combined neural network is applied to predicting object motions in dynamic environments. The ART2 network extracts a set of coherent patterns of the object motion by its self-organizing and unsupervised learning features. The identified patterns are directed to the Madaline network to generate a quantitative prediction of the future motion states. The method does not require any presumption of the mathematical models, and is applicable to a variety of situations.

UR - http://www.scopus.com/inward/record.url?scp=34249753034&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34249753034&partnerID=8YFLogxK

U2 - 10.1007/BF02312378

DO - 10.1007/BF02312378

M3 - Article

VL - 2

SP - 19

EP - 21

JO - Neural Processing Letters

JF - Neural Processing Letters

SN - 1370-4621

IS - 1

ER -