Recognizing em ellipticity patterns with neural networks

Mary M Poulton, Charles E. Glass, Ben K Sternberg

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

The interpretation of surface electromagnetic ellipticity measurements is treated as a pattern recognition problem vis a vis an inverse problem. A parallel distributed processing or neural network approach is used for the pattern recognition. A feed forward, backpropagation network is trained to recognize the spatial location of an anomaly given ellipticity patterns from 20 theoretical models. The network has demonstrated an ability to form abstractions and generalizations when presented with ellipticity patterns that are not part of the training set.

Original languageEnglish (US)
Pages208-212
Number of pages5
StatePublished - Jan 1 1989
Event1989 Society of Exploration Geophysicists Annual Meeting, SEG 1989 - Dallas, United States
Duration: Oct 29 1989Nov 2 1989

Other

Other1989 Society of Exploration Geophysicists Annual Meeting, SEG 1989
CountryUnited States
CityDallas
Period10/29/8911/2/89

Fingerprint

pattern recognition
ellipticity
inverse problem
distributed processing
anomaly
education
anomalies
electromagnetism

ASJC Scopus subject areas

  • Geophysics

Cite this

Poulton, M. M., Glass, C. E., & Sternberg, B. K. (1989). Recognizing em ellipticity patterns with neural networks. 208-212. Paper presented at 1989 Society of Exploration Geophysicists Annual Meeting, SEG 1989, Dallas, United States.

Recognizing em ellipticity patterns with neural networks. / Poulton, Mary M; Glass, Charles E.; Sternberg, Ben K.

1989. 208-212 Paper presented at 1989 Society of Exploration Geophysicists Annual Meeting, SEG 1989, Dallas, United States.

Research output: Contribution to conferencePaper

Poulton, MM, Glass, CE & Sternberg, BK 1989, 'Recognizing em ellipticity patterns with neural networks' Paper presented at 1989 Society of Exploration Geophysicists Annual Meeting, SEG 1989, Dallas, United States, 10/29/89 - 11/2/89, pp. 208-212.
Poulton MM, Glass CE, Sternberg BK. Recognizing em ellipticity patterns with neural networks. 1989. Paper presented at 1989 Society of Exploration Geophysicists Annual Meeting, SEG 1989, Dallas, United States.
Poulton, Mary M ; Glass, Charles E. ; Sternberg, Ben K. / Recognizing em ellipticity patterns with neural networks. Paper presented at 1989 Society of Exploration Geophysicists Annual Meeting, SEG 1989, Dallas, United States.5 p.
@conference{45d5fc5f34dd46938d9df80d5d84d4e5,
title = "Recognizing em ellipticity patterns with neural networks",
abstract = "The interpretation of surface electromagnetic ellipticity measurements is treated as a pattern recognition problem vis a vis an inverse problem. A parallel distributed processing or neural network approach is used for the pattern recognition. A feed forward, backpropagation network is trained to recognize the spatial location of an anomaly given ellipticity patterns from 20 theoretical models. The network has demonstrated an ability to form abstractions and generalizations when presented with ellipticity patterns that are not part of the training set.",
author = "Poulton, {Mary M} and Glass, {Charles E.} and Sternberg, {Ben K}",
year = "1989",
month = "1",
day = "1",
language = "English (US)",
pages = "208--212",
note = "1989 Society of Exploration Geophysicists Annual Meeting, SEG 1989 ; Conference date: 29-10-1989 Through 02-11-1989",

}

TY - CONF

T1 - Recognizing em ellipticity patterns with neural networks

AU - Poulton, Mary M

AU - Glass, Charles E.

AU - Sternberg, Ben K

PY - 1989/1/1

Y1 - 1989/1/1

N2 - The interpretation of surface electromagnetic ellipticity measurements is treated as a pattern recognition problem vis a vis an inverse problem. A parallel distributed processing or neural network approach is used for the pattern recognition. A feed forward, backpropagation network is trained to recognize the spatial location of an anomaly given ellipticity patterns from 20 theoretical models. The network has demonstrated an ability to form abstractions and generalizations when presented with ellipticity patterns that are not part of the training set.

AB - The interpretation of surface electromagnetic ellipticity measurements is treated as a pattern recognition problem vis a vis an inverse problem. A parallel distributed processing or neural network approach is used for the pattern recognition. A feed forward, backpropagation network is trained to recognize the spatial location of an anomaly given ellipticity patterns from 20 theoretical models. The network has demonstrated an ability to form abstractions and generalizations when presented with ellipticity patterns that are not part of the training set.

UR - http://www.scopus.com/inward/record.url?scp=85036466770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85036466770&partnerID=8YFLogxK

M3 - Paper

SP - 208

EP - 212

ER -