NEURAL NETWORK SCHEME FOR 3-DIMENSIONAL PATTERN RECOGNITION AND CONSTRUCTION.

Yoon Pin Simon Foo, Yoshiyasu Takefuji

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A neural-based scheme for pattern recognition and construction of three-dimensional images from partial cues is presented. Clusters of neural nets operating concurrently are used to learn and recall patterns at X, Y, Z planes. Simulations are performed based on a Hopfield-like network to investigate the effect of learning trials and firing percentage of nodes per cycle. A method for computing the common features of input patterns is given. Results showed that maximum parallel processing can be achieved.

Original languageEnglish
Title of host publicationUnknown Host Publication Title
EditorsMaureen Caudill, Charles T. Butler, San Diego Adaptics
PublisherSOS Printing
Publication statusPublished - 1987
Externally publishedYes

Fingerprint

Pattern recognition
Neural networks
Processing

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Foo, Y. P. S., & Takefuji, Y. (1987). NEURAL NETWORK SCHEME FOR 3-DIMENSIONAL PATTERN RECOGNITION AND CONSTRUCTION. In M. Caudill, C. T. Butler, & S. D. Adaptics (Eds.), Unknown Host Publication Title SOS Printing.

NEURAL NETWORK SCHEME FOR 3-DIMENSIONAL PATTERN RECOGNITION AND CONSTRUCTION. / Foo, Yoon Pin Simon; Takefuji, Yoshiyasu.

Unknown Host Publication Title. ed. / Maureen Caudill; Charles T. Butler; San Diego Adaptics. SOS Printing, 1987.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Foo, YPS & Takefuji, Y 1987, NEURAL NETWORK SCHEME FOR 3-DIMENSIONAL PATTERN RECOGNITION AND CONSTRUCTION. in M Caudill, CT Butler & SD Adaptics (eds), Unknown Host Publication Title. SOS Printing.
Foo YPS, Takefuji Y. NEURAL NETWORK SCHEME FOR 3-DIMENSIONAL PATTERN RECOGNITION AND CONSTRUCTION. In Caudill M, Butler CT, Adaptics SD, editors, Unknown Host Publication Title. SOS Printing. 1987
Foo, Yoon Pin Simon ; Takefuji, Yoshiyasu. / NEURAL NETWORK SCHEME FOR 3-DIMENSIONAL PATTERN RECOGNITION AND CONSTRUCTION. Unknown Host Publication Title. editor / Maureen Caudill ; Charles T. Butler ; San Diego Adaptics. SOS Printing, 1987.
@inproceedings{1f8c271009334cbaa005acbbfb1b0e76,
title = "NEURAL NETWORK SCHEME FOR 3-DIMENSIONAL PATTERN RECOGNITION AND CONSTRUCTION.",
abstract = "A neural-based scheme for pattern recognition and construction of three-dimensional images from partial cues is presented. Clusters of neural nets operating concurrently are used to learn and recall patterns at X, Y, Z planes. Simulations are performed based on a Hopfield-like network to investigate the effect of learning trials and firing percentage of nodes per cycle. A method for computing the common features of input patterns is given. Results showed that maximum parallel processing can be achieved.",
author = "Foo, {Yoon Pin Simon} and Yoshiyasu Takefuji",
year = "1987",
language = "English",
editor = "Maureen Caudill and Butler, {Charles T.} and Adaptics, {San Diego}",
booktitle = "Unknown Host Publication Title",
publisher = "SOS Printing",

}

TY - GEN

T1 - NEURAL NETWORK SCHEME FOR 3-DIMENSIONAL PATTERN RECOGNITION AND CONSTRUCTION.

AU - Foo, Yoon Pin Simon

AU - Takefuji, Yoshiyasu

PY - 1987

Y1 - 1987

N2 - A neural-based scheme for pattern recognition and construction of three-dimensional images from partial cues is presented. Clusters of neural nets operating concurrently are used to learn and recall patterns at X, Y, Z planes. Simulations are performed based on a Hopfield-like network to investigate the effect of learning trials and firing percentage of nodes per cycle. A method for computing the common features of input patterns is given. Results showed that maximum parallel processing can be achieved.

AB - A neural-based scheme for pattern recognition and construction of three-dimensional images from partial cues is presented. Clusters of neural nets operating concurrently are used to learn and recall patterns at X, Y, Z planes. Simulations are performed based on a Hopfield-like network to investigate the effect of learning trials and firing percentage of nodes per cycle. A method for computing the common features of input patterns is given. Results showed that maximum parallel processing can be achieved.

UR - http://www.scopus.com/inward/record.url?scp=18244425294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=18244425294&partnerID=8YFLogxK

M3 - Conference contribution

BT - Unknown Host Publication Title

A2 - Caudill, Maureen

A2 - Butler, Charles T.

A2 - Adaptics, San Diego

PB - SOS Printing

ER -