Decision-based neural networks with signal/image classification applications.
Identifieur interne : 000084 ( PubMed/Corpus ); précédent : 000083; suivant : 000085Decision-based neural networks with signal/image classification applications.
Auteurs : S Y Kung ; J S TaurSource :
- IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council [ 1045-9227 ] ; 1995.
Abstract
Supervised learning networks based on a decision-based formulation are explored. More specifically, a decision-based neural network (DBNN) is proposed, which combines the perceptron-like learning rule and hierarchical nonlinear network structure. The decision-based mutual training can be applied to both static and temporal pattern recognition problems. For static pattern recognition, two hierarchical structures are proposed: hidden-node and subcluster structures. The relationships between DBNN's and other models (linear perceptron, piecewise-linear perceptron, LVQ, and PNN) are discussed. As to temporal DBNN's, model-based discriminant functions may be chosen to compensate possible temporal variations, such as waveform warping and alignments. Typical examples include DTW distance, prediction error, or likelihood functions. For classification applications, DBNN's are very effective in computation time and performance. This is confirmed by simulations conducted for several applications, including texture classification, OCR, and ECG analysis.
DOI: 10.1109/72.363439
PubMed: 18263296
Links to Exploration step
pubmed:18263296Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Decision-based neural networks with signal/image classification applications.</title><author><name sortKey="Kung, S Y" sort="Kung, S Y" uniqKey="Kung S" first="S Y" last="Kung">S Y Kung</name><affiliation><nlm:affiliation>Dept. of Electr. Eng., Princeton Univ., NJ.</nlm:affiliation></affiliation></author><author><name sortKey="Taur, J S" sort="Taur, J S" uniqKey="Taur J" first="J S" last="Taur">J S Taur</name></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="1995">1995</date><idno type="doi">10.1109/72.363439</idno><idno type="RBID">pubmed:18263296</idno><idno type="pmid">18263296</idno><idno type="wicri:Area/PubMed/Corpus">000084</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Decision-based neural networks with signal/image classification applications.</title><author><name sortKey="Kung, S Y" sort="Kung, S Y" uniqKey="Kung S" first="S Y" last="Kung">S Y Kung</name><affiliation><nlm:affiliation>Dept. of Electr. Eng., Princeton Univ., NJ.</nlm:affiliation></affiliation></author><author><name sortKey="Taur, J S" sort="Taur, J S" uniqKey="Taur J" first="J S" last="Taur">J S Taur</name></author></analytic><series><title level="j">IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council</title><idno type="ISSN">1045-9227</idno><imprint><date when="1995" type="published">1995</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Supervised learning networks based on a decision-based formulation are explored. More specifically, a decision-based neural network (DBNN) is proposed, which combines the perceptron-like learning rule and hierarchical nonlinear network structure. The decision-based mutual training can be applied to both static and temporal pattern recognition problems. For static pattern recognition, two hierarchical structures are proposed: hidden-node and subcluster structures. The relationships between DBNN's and other models (linear perceptron, piecewise-linear perceptron, LVQ, and PNN) are discussed. As to temporal DBNN's, model-based discriminant functions may be chosen to compensate possible temporal variations, such as waveform warping and alignments. Typical examples include DTW distance, prediction error, or likelihood functions. For classification applications, DBNN's are very effective in computation time and performance. This is confirmed by simulations conducted for several applications, including texture classification, OCR, and ECG analysis.</div></front></TEI><pubmed><MedlineCitation Owner="NLM" Status="PubMed-not-MEDLINE"><PMID Version="1">18263296</PMID><DateCreated><Year>2008</Year><Month>02</Month><Day>11</Day></DateCreated><DateCompleted><Year>2012</Year><Month>10</Month><Day>02</Day></DateCompleted><Article PubModel="Print"><Journal><ISSN IssnType="Print">1045-9227</ISSN><JournalIssue CitedMedium="Print"><Volume>6</Volume><Issue>1</Issue><PubDate><Year>1995</Year></PubDate></JournalIssue><Title>IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council</Title><ISOAbbreviation>IEEE Trans Neural Netw</ISOAbbreviation></Journal><ArticleTitle>Decision-based neural networks with signal/image classification applications.</ArticleTitle><Pagination><MedlinePgn>170-81</MedlinePgn></Pagination><Abstract><AbstractText>Supervised learning networks based on a decision-based formulation are explored. More specifically, a decision-based neural network (DBNN) is proposed, which combines the perceptron-like learning rule and hierarchical nonlinear network structure. The decision-based mutual training can be applied to both static and temporal pattern recognition problems. For static pattern recognition, two hierarchical structures are proposed: hidden-node and subcluster structures. The relationships between DBNN's and other models (linear perceptron, piecewise-linear perceptron, LVQ, and PNN) are discussed. As to temporal DBNN's, model-based discriminant functions may be chosen to compensate possible temporal variations, such as waveform warping and alignments. Typical examples include DTW distance, prediction error, or likelihood functions. For classification applications, DBNN's are very effective in computation time and performance. This is confirmed by simulations conducted for several applications, including texture classification, OCR, and ECG analysis.</AbstractText></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Kung</LastName><ForeName>S Y</ForeName><Initials>SY</Initials><AffiliationInfo><Affiliation>Dept. of Electr. Eng., Princeton Univ., NJ.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Taur</LastName><ForeName>J S</ForeName><Initials>JS</Initials></Author></AuthorList><Language>eng</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType></PublicationTypeList></Article><MedlineJournalInfo><Country>United States</Country><MedlineTA>IEEE Trans Neural Netw</MedlineTA><NlmUniqueID>101211035</NlmUniqueID><ISSNLinking>1045-9227</ISSNLinking></MedlineJournalInfo></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="pubmed"><Year>1995</Year><Month>1</Month><Day>1</Day><Hour>0</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>1995</Year><Month>1</Month><Day>1</Day><Hour>0</Hour><Minute>1</Minute></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>1995</Year><Month>1</Month><Day>1</Day><Hour>0</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>ppublish</PublicationStatus><ArticleIdList><ArticleId IdType="doi">10.1109/72.363439</ArticleId><ArticleId IdType="pubmed">18263296</ArticleId></ArticleIdList></PubmedData></pubmed></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000084 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000084 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= PubMed
|étape= Corpus
|type= RBID
|clé= pubmed:18263296
|texte= Decision-based neural networks with signal/image classification applications.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:18263296" \
| HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \
| NlmPubMed2Wicri -a OcrV1
| This area was generated with Dilib version V0.6.32. |  |