Sea ice classification using fast learning neural networks
A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics...
Main Authors: | , , |
---|---|
Format: | Other/Unknown Material |
Language: | unknown |
Published: |
1992
|
Subjects: | |
Online Access: | http://ntrs.nasa.gov/search.jsp?R=19930063845 |
id |
ftnasantrs:oai:casi.ntrs.nasa.gov:19930063845 |
---|---|
record_format |
openpolar |
spelling |
ftnasantrs:oai:casi.ntrs.nasa.gov:19930063845 2023-05-15T18:17:30+02:00 Sea ice classification using fast learning neural networks Dawson, M. S. Fung, A. K. Manry, M. T. Unclassified, Unlimited, Publicly available 1992 http://ntrs.nasa.gov/search.jsp?R=19930063845 unknown http://ntrs.nasa.gov/search.jsp?R=19930063845 Accession ID: 93A47842 Copyright Other Sources 48 In: IGARSS '92; Proceedings of the 12th Annual International Geoscience and Remote Sensing Symposium, Houston, TX, May 26-29, 1992. Vol. 2 (A93-47551 20-43); p. 1070, 1071. 1992 ftnasantrs 2012-02-15T20:12:32Z A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics of the target class. Four classes were used in the data simulation: open water, thick lossy saline ice, thin saline ice, and multiyear ice. The BP network was unable to consistently converge to less than 25 percent error while the FL method yielded an average error of approximately 1 percent on the first iteration of training. The fast learning method presented can significantly reduce the CPU time necessary to train a neural network as well as consistently yield higher classification accuracy than BP networks. Other/Unknown Material Sea ice NASA Technical Reports Server (NTRS) |
institution |
Open Polar |
collection |
NASA Technical Reports Server (NTRS) |
op_collection_id |
ftnasantrs |
language |
unknown |
topic |
48 |
spellingShingle |
48 Dawson, M. S. Fung, A. K. Manry, M. T. Sea ice classification using fast learning neural networks |
topic_facet |
48 |
description |
A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics of the target class. Four classes were used in the data simulation: open water, thick lossy saline ice, thin saline ice, and multiyear ice. The BP network was unable to consistently converge to less than 25 percent error while the FL method yielded an average error of approximately 1 percent on the first iteration of training. The fast learning method presented can significantly reduce the CPU time necessary to train a neural network as well as consistently yield higher classification accuracy than BP networks. |
format |
Other/Unknown Material |
author |
Dawson, M. S. Fung, A. K. Manry, M. T. |
author_facet |
Dawson, M. S. Fung, A. K. Manry, M. T. |
author_sort |
Dawson, M. S. |
title |
Sea ice classification using fast learning neural networks |
title_short |
Sea ice classification using fast learning neural networks |
title_full |
Sea ice classification using fast learning neural networks |
title_fullStr |
Sea ice classification using fast learning neural networks |
title_full_unstemmed |
Sea ice classification using fast learning neural networks |
title_sort |
sea ice classification using fast learning neural networks |
publishDate |
1992 |
url |
http://ntrs.nasa.gov/search.jsp?R=19930063845 |
op_coverage |
Unclassified, Unlimited, Publicly available |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
Other Sources |
op_relation |
http://ntrs.nasa.gov/search.jsp?R=19930063845 Accession ID: 93A47842 |
op_rights |
Copyright |
_version_ |
1766191755427840000 |