Matches in SemOpenAlex for { <https://semopenalex.org/work/W2010250397> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2010250397 endingPage "604" @default.
- W2010250397 startingPage "601" @default.
- W2010250397 abstract "Learning vector quantization networks are generally considered a powerful pattern recognition tool. Their main drawback, however, is the competitive learning algorithm they are based upon, that suffers of the so called underutilized or dead unit problem. To solve this problem, algorithms substantially based on a modified distance calculation, such as the frequency sensitive competitive learning (FSCL), have been proposed, but their attainable performance strongly depends on the selection of an appropriate number of neurons. This choice generally require knowledge about the number of clusters in the feature space. We propose a new supervised training algorithm for LVQ neural networks, which provide the optimal number of neurons for each class by dynamically adding or removing neurons on the basis of a measure of their performance. The experimental results, performed on different databases of synthetic data, confirmed the effectiveness of our approach." @default.
- W2010250397 created "2016-06-24" @default.
- W2010250397 creator A5010444228 @default.
- W2010250397 creator A5048265453 @default.
- W2010250397 creator A5057804135 @default.
- W2010250397 date "2004-08-23" @default.
- W2010250397 modified "2023-09-23" @default.
- W2010250397 title "A dynamic approach to learning vector quantization" @default.
- W2010250397 cites W1587362683 @default.
- W2010250397 cites W1991848143 @default.
- W2010250397 cites W2002182716 @default.
- W2010250397 cites W2071781501 @default.
- W2010250397 cites W2098929365 @default.
- W2010250397 cites W2107588225 @default.
- W2010250397 cites W2133515443 @default.
- W2010250397 cites W2168993425 @default.
- W2010250397 cites W2913399920 @default.
- W2010250397 doi "https://doi.org/10.1109/icpr.2004.26" @default.
- W2010250397 hasPublicationYear "2004" @default.
- W2010250397 type Work @default.
- W2010250397 sameAs 2010250397 @default.
- W2010250397 citedByCount "4" @default.
- W2010250397 countsByYear W20102503972012 @default.
- W2010250397 crossrefType "proceedings-article" @default.
- W2010250397 hasAuthorship W2010250397A5010444228 @default.
- W2010250397 hasAuthorship W2010250397A5048265453 @default.
- W2010250397 hasAuthorship W2010250397A5057804135 @default.
- W2010250397 hasConcept C11413529 @default.
- W2010250397 hasConcept C119857082 @default.
- W2010250397 hasConcept C120822770 @default.
- W2010250397 hasConcept C136389625 @default.
- W2010250397 hasConcept C153180895 @default.
- W2010250397 hasConcept C154945302 @default.
- W2010250397 hasConcept C199833920 @default.
- W2010250397 hasConcept C28855332 @default.
- W2010250397 hasConcept C40567965 @default.
- W2010250397 hasConcept C41008148 @default.
- W2010250397 hasConcept C50644808 @default.
- W2010250397 hasConcept C8038995 @default.
- W2010250397 hasConcept C83665646 @default.
- W2010250397 hasConceptScore W2010250397C11413529 @default.
- W2010250397 hasConceptScore W2010250397C119857082 @default.
- W2010250397 hasConceptScore W2010250397C120822770 @default.
- W2010250397 hasConceptScore W2010250397C136389625 @default.
- W2010250397 hasConceptScore W2010250397C153180895 @default.
- W2010250397 hasConceptScore W2010250397C154945302 @default.
- W2010250397 hasConceptScore W2010250397C199833920 @default.
- W2010250397 hasConceptScore W2010250397C28855332 @default.
- W2010250397 hasConceptScore W2010250397C40567965 @default.
- W2010250397 hasConceptScore W2010250397C41008148 @default.
- W2010250397 hasConceptScore W2010250397C50644808 @default.
- W2010250397 hasConceptScore W2010250397C8038995 @default.
- W2010250397 hasConceptScore W2010250397C83665646 @default.
- W2010250397 hasLocation W20102503971 @default.
- W2010250397 hasOpenAccess W2010250397 @default.
- W2010250397 hasPrimaryLocation W20102503971 @default.
- W2010250397 hasRelatedWork W1981329174 @default.
- W2010250397 hasRelatedWork W2030901812 @default.
- W2010250397 hasRelatedWork W2048907071 @default.
- W2010250397 hasRelatedWork W2110158084 @default.
- W2010250397 hasRelatedWork W2119499964 @default.
- W2010250397 hasRelatedWork W2141756128 @default.
- W2010250397 hasRelatedWork W2143393652 @default.
- W2010250397 hasRelatedWork W2148111537 @default.
- W2010250397 hasRelatedWork W2152159227 @default.
- W2010250397 hasRelatedWork W2154439236 @default.
- W2010250397 hasRelatedWork W2159458863 @default.
- W2010250397 hasRelatedWork W2225087728 @default.
- W2010250397 hasRelatedWork W2378055735 @default.
- W2010250397 hasRelatedWork W2896230333 @default.
- W2010250397 hasRelatedWork W2946622818 @default.
- W2010250397 hasRelatedWork W3019470174 @default.
- W2010250397 hasRelatedWork W3146781226 @default.
- W2010250397 hasRelatedWork W3198609354 @default.
- W2010250397 hasRelatedWork W1975223937 @default.
- W2010250397 hasRelatedWork W2172035917 @default.
- W2010250397 hasVolume "4" @default.
- W2010250397 isParatext "false" @default.
- W2010250397 isRetracted "false" @default.
- W2010250397 magId "2010250397" @default.
- W2010250397 workType "article" @default.