On the performance of neuronal matching algorithms

For a solution of the visual correspondence problem we have modified the Self Organizing Map (SOM) to map image planes onto another in a neighborhood- and feature-preserving way. We have investigated the convergence speed of this SOM and Dynamic Link Matching (DLM) on a benchmark problem for the sol...

Full description

Saved in:

Bibliographic Details
Published in	Neural networks Vol. 12; no. 1; pp. 127 - 134
Main Authors	Würtz, Rolf P, Konen, Wolfgang, Behrmann, Kay-Ole
Format	Journal Article
Language	English
Published	Oxford Elsevier Ltd 1999 Elsevier Science
Subjects	Algorithmics. Computability. Computer arithmetics Applied sciences Artificial intelligence Complexity Computer science; control theory; systems Connectionism. Neural networks Convergence speed Correspondence problem Dynamic link matching Exact sciences and technology Self-organizing map Symmetry recognition Theoretical computing Dynamic link matching Correspondence problem Symmetry recognition Self-organizing map Convergence speed Complexity Self organization Maps Theoretical study Correspondence principle Dynamic model Link
Online Access	Get full text
ISSN	0893-6080 1879-2782 1879-2782
DOI	10.1016/S0893-6080(98)00112-9

Cover

Abstract	For a solution of the visual correspondence problem we have modified the Self Organizing Map (SOM) to map image planes onto another in a neighborhood- and feature-preserving way. We have investigated the convergence speed of this SOM and Dynamic Link Matching (DLM) on a benchmark problem for the solution of which both algorithms are good candidates. We show that even after careful parameter adjustment the SOM needs a large number of simple update steps and DLM a small number of complicated ones. The results are consistent with an exponential vs. polynomial scaling behavior with increased pattern size. Finally, we present and motivate a rule for adjusting the parameters of DLM for all problem sizes, which we could not find for SOM.
AbstractList	For a solution of the visual correspondence problem we have modified the Self Organizing Map (SOM) to map image planes onto another in a neighborhood- and feature-preserving way. We have investigated the convergence speed of this SOM and Dynamic Link Matching (DLM) on a benchmark problem for the solution of which both algorithms are good candidates. We show that even after careful parameter adjustment the SOM needs a large number of simple update steps and DLM a small number of complicated ones. The results are consistent with an exponential vs. polynomial scaling behavior with increased pattern size. Finally, we present and motivate a rule for adjusting the parameters of DLM for all problem sizes, which we could not find for SOM. For a solution of the visual correspondence problem we have modified the Self Organizing Map (SOM) to map image planes onto another in a neighborhood- and feature-preserving way. We have investigated the convergence speed of this SOM and Dynamic Link Matching (DLM) on a benchmark problem for the solution of which both algorithms are good candidates. We show that even after careful parameter adjustment the SOM needs a large number of simple update steps and DLM a small number of complicated ones. The results are consistent with an exponential vs. polynomial scaling behavior with increased pattern size. Finally, we present and motivate a rule for adjusting the parameters of DLM for all problem sizes, which we could not find for SOM.For a solution of the visual correspondence problem we have modified the Self Organizing Map (SOM) to map image planes onto another in a neighborhood- and feature-preserving way. We have investigated the convergence speed of this SOM and Dynamic Link Matching (DLM) on a benchmark problem for the solution of which both algorithms are good candidates. We show that even after careful parameter adjustment the SOM needs a large number of simple update steps and DLM a small number of complicated ones. The results are consistent with an exponential vs. polynomial scaling behavior with increased pattern size. Finally, we present and motivate a rule for adjusting the parameters of DLM for all problem sizes, which we could not find for SOM.
Author	Behrmann, Kay-Ole Konen, Wolfgang Würtz, Rolf P
Author_xml	– sequence: 1 givenname: Rolf P surname: Würtz fullname: Würtz, Rolf P email: rolf.wuertz@neuroinformatik.ruhr-uni-bochum.de organization: Institut für Neuroinformatik, Ruhr-Universität Bochum, D-44780 Bochum, Germany – sequence: 2 givenname: Wolfgang surname: Konen fullname: Konen, Wolfgang organization: Zentrum für Neuroinformatik GmbH, Bochum, Germany – sequence: 3 givenname: Kay-Ole surname: Behrmann fullname: Behrmann, Kay-Ole organization: Institut für Neuroinformatik, Ruhr-Universität Bochum, D-44780 Bochum, Germany
BackLink	https://cir.nii.ac.jp/crid/1570009749812420736$$DView record in CiNii http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=1868184$$DView record in Pascal Francis https://www.ncbi.nlm.nih.gov/pubmed/12662721$$D View this record in MEDLINE/PubMed
BookMark	eNqFkc1rFDEYh4NU7Hbrn6DMQaQ9jM2bzOQDDyLFWqHQg_Uc0sw73chMsiZZwf_ebHdbwUN7yJvL837we47IQYgBCXkD9ANQEGffqdK8FVTRE61OKQVgrX5BFqCkbplU7IAsHpFDcpTzT0qpUB1_RQ6BCcEkgwVh16EpK2zWmMaYZhscNnFsAm5SDHZqZlvcyoe7xk53MfmymvMxeTnaKePr_b8kPy6-3JxftlfXX7-df75qXdez0jqhuesdypEPA3agcRQccQDpHAeKSliBCgQDiz2_5b1lSg6KDopzbS3jS_J-N3ed4q8N5mJmnx1Okw0YN9kwSXutGFTw5EkQVK-51vVV9O0e3dzOOJh18rNNf8xDIBV4twdsdnYaU03E53-cEgpqhkvycYe5FHNOOBrniy0-hpKsnwxQs7Vk7i2ZrQKjlbm3ZLZX9P91P85_pm9_XPC-LtxW6GXVqmWnFbCOUclFxT7tMKx2fntMJjuP1ezgE7pihuifWfQXoB2xaQ
CitedBy_id	crossref_primary_10_1016_j_patrec_2003_10_012
Cites_doi	10.1109/ICNN.1996.549171 10.1016/S0893-6080(05)80157-1 10.1109/12.210173 10.1109/34.598234 10.1098/rspb.1976.0087 10.1162/neco.1993.5.5.719 10.1007/BF00337288 10.1109/5.58325 10.1016/0167-2789(86)90245-9 10.1007/978-3-642-97966-8
ContentType	Journal Article
Copyright	1998 Elsevier Science Ltd 1999 INIST-CNRS
Copyright_xml	– notice: 1998 Elsevier Science Ltd – notice: 1999 INIST-CNRS
DBID	RYH AAYXX CITATION IQODW NPM 7X8 7SC 8FD JQ2 L7M L~C L~D
DOI	10.1016/S0893-6080(98)00112-9
DatabaseName	CiNii Complete CrossRef Pascal-Francis PubMed MEDLINE - Academic Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef PubMed MEDLINE - Academic Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional
DatabaseTitleList	PubMed MEDLINE - Academic Computer and Information Systems Abstracts
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science Applied Sciences
EISSN	1879-2782
EndPage	134
ExternalDocumentID	12662721 1868184 10_1016_S0893_6080_98_00112_9 10009398905 S0893608098001129
Genre	Journal Article
GroupedDBID	--- --K --M -~X .DC .~1 0R~ 123 186 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5RE 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXLA AAXUO AAYFN ABAOU ABBOA ABCQJ ABEFU ABFNM ABFRF ABHFT ABIVO ABJNI ABLJU ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFO ACGFS ACIUM ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADRHT AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HMQ HVGLF HZ~ IHE J1W JJJVA K-O KOM KZ1 LG9 LMP M2V M41 MHUIS MO0 MOBAO MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SNS SPC SPCBC SSN SST SSV SSW SSZ T5K TAE UAP UNMZH VOH WUQ XPP ZMT ~G- AATTM AAXKI AAYWO ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFPUW AGCQF AGQPQ AGRNS AIIUN AKBMS AKRWK AKYEP ANKPU RYH SSH AAYXX ABDPE ACLOT AFJKZ AIGII APXCP CITATION EFKBS ~HD BNPGV IQODW NPM PKN 7X8 7SC 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c452t-c693c5ce7f3dde419ef63eed17cc310e86a6e81621ae53b35a287d80d8339aa23
IEDL.DBID	AIKHN
ISSN	0893-6080 1879-2782
IngestDate	Wed Oct 01 14:21:45 EDT 2025 Sat Sep 27 15:58:46 EDT 2025 Wed Feb 19 01:40:48 EST 2025 Mon Jul 21 09:11:18 EDT 2025 Wed Oct 01 02:07:34 EDT 2025 Thu Apr 24 22:56:05 EDT 2025 Thu Jun 26 21:53:52 EDT 2025 Fri Feb 23 02:29:03 EST 2024
IsPeerReviewed	true
IsScholarly	true
Issue	1
Keywords	Dynamic link matching Correspondence problem Symmetry recognition Self-organizing map Convergence speed Complexity Self organization Maps Theoretical study Correspondence principle Dynamic model Link
Language	English
License	https://www.elsevier.com/tdm/userlicense/1.0 CC BY 4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c452t-c693c5ce7f3dde419ef63eed17cc310e86a6e81621ae53b35a287d80d8339aa23
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Article-2 ObjectType-Feature-1
PMID	12662721
PQID	1859399939
PQPubID	23479
PageCount	8
ParticipantIDs	proquest_miscellaneous_27059821 proquest_miscellaneous_1859399939 pubmed_primary_12662721 pascalfrancis_primary_1868184 crossref_citationtrail_10_1016_S0893_6080_98_00112_9 crossref_primary_10_1016_S0893_6080_98_00112_9 nii_cinii_1570009749812420736 elsevier_sciencedirect_doi_10_1016_S0893_6080_98_00112_9
ProviderPackageCode	CITATION AAYXX
PublicationCentury	1900
PublicationDate	1999 1999-01-01 1999-1-00 1999-Jan 19990101
PublicationDateYYYYMMDD	1999-01-01
PublicationDate_xml	– year: 1999 text: 1999
PublicationDecade	1990
PublicationPlace	Oxford
PublicationPlace_xml	– name: Oxford – name: United States
PublicationTitle	Neural networks
PublicationTitleAlternate	Neural Netw
PublicationYear	1999
Publisher	Elsevier Ltd Elsevier Science
Publisher_xml	– name: Elsevier Ltd – name: Elsevier Science
References	(Vol. 41). Thun, Frankfurt am Main: Verlag Harri Deutsch. Konen, Maurer, von der Malsburg (BIB8) 1994; 7 Thun, Frankfurt am Main: Verlag Harri Deutsch. Sejnowski, Kienker, Hinton (BIB10) 1986; 22 Willshaw, von der Malsburg (BIB11) 1976; 194 Lades, Vorbrüggen, Buhmann, Lange, von der Malsburg, Würtz, Konen (BIB9) 1993; 42 Wiskott, L. (1996). Labeled graphs and dynamic link matching for face recognition and scene analysis. In Bellando, J. and Kothari, R. (1996). On image correspondence using topology preserving mappings. In Austin, TX: The UTCS Neural Networks Research Group, Electronic Book, ISBN 0-9647060-0-8, http://www.cs.utexas.edu/users/nn/web-pubs/htmlbook96. Kohonen, T. (1997). Konen, von der Malsburg (BIB7) 1993; 5 Washington, 1996 (pp. 1784–1789). Kohonen (BIB5) 1990; 78 Kohonen (BIB4) 1982; 43 (2nd Ed.). Berlin, Heidelberg, New York: Springer Verlag. Würtz, R. P. (1995). Multilayer dynamic link networks for establishing image point correspondences and visual object recognition. In Würtz (BIB15) 1997; 19 Behrmann, K. -O. (1993). Leistungsuntersuchungen des `Dynamischen Link-matchings' und Vergleich mit dem Kohonen-Algorithmus. Technical Report IR-INI 93-05, Ruhr-Universität Bochum; Master's Thesis, Universität Karlsruhe. Wiskott, L. and von der Malsburg, C. (1996). Face recognition by dynamic link matching. In J. Sirosh, R. Miikkulainen and Y. Choe (Eds.) Goodhill, G. J., Finch, S., and Sejnowski, T. J. (1995). Quantifying neighborhood preservation in topographic mappings. Technical Report INC-9505. Institute for Neural Computation, UCSD, La Jolla, CA 92037, USA. 10.1016/S0893-6080(98)00112-9_BIB1 Lades (10.1016/S0893-6080(98)00112-9_BIB9) 1993; 42 Sejnowski (10.1016/S0893-6080(98)00112-9_BIB10) 1986; 22 10.1016/S0893-6080(98)00112-9_BIB13 10.1016/S0893-6080(98)00112-9_BIB14 Würtz (10.1016/S0893-6080(98)00112-9_BIB15) 1997; 19 Konen (10.1016/S0893-6080(98)00112-9_BIB7) 1993; 5 10.1016/S0893-6080(98)00112-9_BIB12 Kohonen (10.1016/S0893-6080(98)00112-9_BIB4) 1982; 43 10.1016/S0893-6080(98)00112-9_BIB6 Kohonen (10.1016/S0893-6080(98)00112-9_BIB5) 1990; 78 10.1016/S0893-6080(98)00112-9_BIB2 Konen (10.1016/S0893-6080(98)00112-9_BIB8) 1994; 7 10.1016/S0893-6080(98)00112-9_BIB3 Willshaw (10.1016/S0893-6080(98)00112-9_BIB11) 1976; 194
References_xml	– volume: 43 start-page: 59 year: 1982 end-page: 69 ident: BIB4 article-title: Self-organized formation of topologically correct feature maps publication-title: Biological Cybernetics – reference: Bellando, J. and Kothari, R. (1996). On image correspondence using topology preserving mappings. In – volume: 78 start-page: 1464 year: 1990 end-page: 1480 ident: BIB5 article-title: The self-organizing map publication-title: Proc. IEEE – reference: Wiskott, L. (1996). Labeled graphs and dynamic link matching for face recognition and scene analysis. In – reference: . Austin, TX: The UTCS Neural Networks Research Group, Electronic Book, ISBN 0-9647060-0-8, http://www.cs.utexas.edu/users/nn/web-pubs/htmlbook96. – volume: 22 start-page: 260 year: 1986 end-page: 275 ident: BIB10 article-title: Learning symmetry groups with hidden units: beyond the perceptron publication-title: Physica D – reference: Wiskott, L. and von der Malsburg, C. (1996). Face recognition by dynamic link matching. In J. Sirosh, R. Miikkulainen and Y. Choe (Eds.), – volume: 194 start-page: 431 year: 1976 end-page: 445 ident: BIB11 article-title: How patterned neural connections can be set up by self-organization publication-title: Proceedings of the Royal Society, London, B – volume: 19 start-page: 769 year: 1997 end-page: 775 ident: BIB15 article-title: Object recognition robust under translations, deformations and changes in background publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – reference: Goodhill, G. J., Finch, S., and Sejnowski, T. J. (1995). Quantifying neighborhood preservation in topographic mappings. Technical Report INC-9505. Institute for Neural Computation, UCSD, La Jolla, CA 92037, USA. – reference: (2nd Ed.). Berlin, Heidelberg, New York: Springer Verlag. – reference: , Washington, 1996 (pp. 1784–1789). – reference: Kohonen, T. (1997). – reference: . Thun, Frankfurt am Main: Verlag Harri Deutsch. – volume: 7 start-page: 1019 year: 1994 end-page: 1030 ident: BIB8 article-title: A fast dynamic link matching algorithm for invariant pattern recognition publication-title: Neural Networks – reference: Würtz, R. P. (1995). Multilayer dynamic link networks for establishing image point correspondences and visual object recognition. In – reference: (Vol. 41). Thun, Frankfurt am Main: Verlag Harri Deutsch. – volume: 5 start-page: 719 year: 1993 end-page: 735 ident: BIB7 article-title: Learning to generalize from single examples in the dynamic link architecture publication-title: Neural Computation – volume: 42 start-page: 300 year: 1993 end-page: 311 ident: BIB9 article-title: Distortion invariant object recognition in the dynamic link architecture publication-title: IEEE Transactions on Computers – reference: Behrmann, K. -O. (1993). Leistungsuntersuchungen des `Dynamischen Link-matchings' und Vergleich mit dem Kohonen-Algorithmus. Technical Report IR-INI 93-05, Ruhr-Universität Bochum; Master's Thesis, Universität Karlsruhe. – ident: 10.1016/S0893-6080(98)00112-9_BIB2 doi: 10.1109/ICNN.1996.549171 – volume: 7 start-page: 1019 issue: 6 year: 1994 ident: 10.1016/S0893-6080(98)00112-9_BIB8 article-title: A fast dynamic link matching algorithm for invariant pattern recognition publication-title: Neural Networks doi: 10.1016/S0893-6080(05)80157-1 – volume: 42 start-page: 300 issue: 3 year: 1993 ident: 10.1016/S0893-6080(98)00112-9_BIB9 article-title: Distortion invariant object recognition in the dynamic link architecture publication-title: IEEE Transactions on Computers doi: 10.1109/12.210173 – volume: 19 start-page: 769 issue: 7 year: 1997 ident: 10.1016/S0893-6080(98)00112-9_BIB15 article-title: Object recognition robust under translations, deformations and changes in background publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/34.598234 – ident: 10.1016/S0893-6080(98)00112-9_BIB13 – ident: 10.1016/S0893-6080(98)00112-9_BIB14 – ident: 10.1016/S0893-6080(98)00112-9_BIB12 – volume: 194 start-page: 431 year: 1976 ident: 10.1016/S0893-6080(98)00112-9_BIB11 article-title: How patterned neural connections can be set up by self-organization publication-title: Proceedings of the Royal Society, London, B doi: 10.1098/rspb.1976.0087 – volume: 5 start-page: 719 year: 1993 ident: 10.1016/S0893-6080(98)00112-9_BIB7 article-title: Learning to generalize from single examples in the dynamic link architecture publication-title: Neural Computation doi: 10.1162/neco.1993.5.5.719 – volume: 43 start-page: 59 year: 1982 ident: 10.1016/S0893-6080(98)00112-9_BIB4 article-title: Self-organized formation of topologically correct feature maps publication-title: Biological Cybernetics doi: 10.1007/BF00337288 – ident: 10.1016/S0893-6080(98)00112-9_BIB3 – volume: 78 start-page: 1464 year: 1990 ident: 10.1016/S0893-6080(98)00112-9_BIB5 article-title: The self-organizing map publication-title: Proc. IEEE doi: 10.1109/5.58325 – ident: 10.1016/S0893-6080(98)00112-9_BIB1 – volume: 22 start-page: 260 year: 1986 ident: 10.1016/S0893-6080(98)00112-9_BIB10 article-title: Learning symmetry groups with hidden units: beyond the perceptron publication-title: Physica D doi: 10.1016/0167-2789(86)90245-9 – ident: 10.1016/S0893-6080(98)00112-9_BIB6 doi: 10.1007/978-3-642-97966-8
SSID	ssj0006843
Score	1.5744056
Snippet	For a solution of the visual correspondence problem we have modified the Self Organizing Map (SOM) to map image planes onto another in a neighborhood- and...
SourceID	proquest pubmed pascalfrancis crossref nii elsevier
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	127
SubjectTerms	Algorithmics. Computability. Computer arithmetics Applied sciences Artificial intelligence Complexity Computer science; control theory; systems Connectionism. Neural networks Convergence speed Correspondence problem Dynamic link matching Exact sciences and technology Self-organizing map Symmetry recognition Theoretical computing
Title	On the performance of neuronal matching algorithms
URI	https://dx.doi.org/10.1016/S0893-6080(98)00112-9 https://cir.nii.ac.jp/crid/1570009749812420736 https://www.ncbi.nlm.nih.gov/pubmed/12662721 https://www.proquest.com/docview/1859399939 https://www.proquest.com/docview/27059821
Volume	12
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: Elsevier SD Complete Freedom Collection [SCCMFC] customDbUrl: eissn: 1879-2782 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0006843 issn: 0893-6080 databaseCode: ACRLP dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: ScienceDirect (Elsevier) customDbUrl: eissn: 1879-2782 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0006843 issn: 0893-6080 databaseCode: .~1 dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: ScienceDirect Freedom Collection Journals customDbUrl: eissn: 1879-2782 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0006843 issn: 0893-6080 databaseCode: AIKHN dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVLSH databaseName: Elsevier Journals customDbUrl: mediaType: online eissn: 1879-2782 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0006843 issn: 0893-6080 databaseCode: AKRWK dateStart: 19930101 isFulltext: true providerName: Library Specific Holdings
link	http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NT9swFH-i7WUXGNtgYYMFaQc4mMZ24tjHClGVTbDDqMQtclybRYK0ou2Vv33P-SDiUFXikBwcvyfn2X7v5-R9APyMEodmzRiSyoSRWKcxyZ2hxKU8jazRylWBtDe3YjKNf90n9ztw2cbCeLfKRvfXOr3S1k3LsJHmcFEUw78RmlqBgEdJj2uY6sEA7Y-UfRiMrn9Pbl8VspC18xz2J56gC-SpmVSNZ0qeV3yI2mSiemVReN9JvUTxubruxWZgWhmo8UfYbZBlOKoHvw87tvwEe23VhrDZxJ-B_SlDRH3hogsZCOcurBJbegYIYSv_ylA_Psyfi9W_p-UXmI6v7i4npKmcQEycsBUxQnGTGJs6juorpso6wdEa0tQYxHNWCi2spIJRbROe80TjwWkmo5nkXGnN-AH0y3lpv0LIcyu1Qynl1sZCWoVMleZuxl3qDNMBxK2wMtOkFffVLR6zzn8MqTMv40zJyoeOZSqAi1eyRZ1XYxuBbGcie7NAMtT920iPceZwdP5OfUL_CE9RykMbhhpO4PM3c9oNSArEM3EAp-0cZ7j5_B8VXdr5eokdEoUID68Afmzow9LIJ0mkARzWy6Njz3z2fUaP3v9q3-BDnUfCfxP6Dv3V89oeI0pa5SfQu3ihJ81e-A952Ad-
linkProvider	Elsevier
linkToHtml	http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9wwEB4BPbQX6BPCo6RSD-3BbGInfhwRKloo0ENB4mY5XhsiQXbFLld-O2MnacRhhdRDcnDskTNjz3xO5gHwPSs9mjVriZAlJYURBam8zYkXTGTOGuVjIO35BR9fFafX5fUKHPWxMMGtstP9rU6P2rprGXXcHM3qevQ3Q1PLEfAoGXANVavwpiipCCewg6fBz4PL1nUOe5PQfQjjaUnExh9K_oxUiFpmoFabug6ek2aOzPNt1YvlsDSap-P3sN7hyvSwnfoHWHHNR9joazak3Rb-BPRPkyLmS2dDwEA69WlMaxkIIICN3pWpubuZPtSL2_v5Z7g6_nV5NCZd3QRikQELYrlitrROeIbKq8iV85yhLcyFtYjmnOSGO5lzmhtXsoqVBo9NE5lNJGPKGMq-wFozbdwWpKxy0njkUuVcwaVTSFQZ5ifMC2-pSaDomaVtl1Q81La404P3GI7WgcdayehBR7VK4ODfsFmbVeO1AbKXhH6xPDRq_teG7qHkcHbhnod0_hmeoVQANhT1G8fnL2Q6TEhyRDNFAt96GWvceuF_imnc9HGOHUqF-A6vBPaX9KEiCykS8wQ22-UxkKch9z7Nt___1fbh7fjy_EyfnVz83oF3bUaJ8HVoF9YWD49uD_HSovoa98Mzm_AIRg
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=On+the+performance+of+neuronal+matching+algorithms&rft.jtitle=Neural+networks&rft.au=W%C3%BCrtz%2C+Rolf+P&rft.au=Konen%2C+Wolfgang&rft.au=Behrmann%2C+Kay-Ole&rft.date=1999&rft.pub=Elsevier+Ltd&rft.issn=0893-6080&rft.eissn=1879-2782&rft.volume=12&rft.issue=1&rft.spage=127&rft.epage=134&rft_id=info:doi/10.1016%2FS0893-6080%2898%2900112-9&rft.externalDocID=S0893608098001129
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon