DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, D | - |
dc.contributor.author | Sunha Ahn | - |
dc.contributor.author | Dae-seong Kang | - |
dc.date.accessioned | 2016-03-31T08:31:39Z | - |
dc.date.available | 2016-03-31T08:31:39Z | - |
dc.date.created | 2013-06-07 | - |
dc.date.issued | 2000-01 | - |
dc.identifier.issn | 0925-2312 | - |
dc.identifier.other | 2000-OAK-0000027640 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/15506 | - |
dc.description.abstract | This paper proposes two co-adaptation schemes of self-organizing maps that incorporate the Kohonen's learning into the GA evolution in an attempt to find an optimal vector quantization codebook of images. The Kohonen's learning rule used for vector quantization of images is sensitive to the choice of its initial parameters and the resultant codebook does not guarantee a minimum distortion. To tackle these problems, we co-adapt the codebooks by evolution and learning in a way that the evolution performs the global search and makes inter-codebook adjustments by altering the codebook structures while the learning performs the local search and makes intra-codebook adjustments by making each codebook''s distortion small. Two kinds of co-adaptation schemes such as Lamarckian and Baldwin co-adaptation are considered in our work. Simulation results show that the evolution guided by a local learning provides the fast convergence, the co-adapted codebook produces better reconstruction image quality than the non-learned equivalent, and Lamarckian co-adaptation turns out more appropriate for the VQ problem. (C) 2000 Elsevier Science B.V. All rights reserved. | - |
dc.description.statementofresponsibility | X | - |
dc.language | English | - |
dc.publisher | NeuroComputing | - |
dc.relation.isPartOf | NeuroComputing | - |
dc.subject | self-organizing map | - |
dc.subject | vector quantization | - |
dc.subject | Kohonen&apos | - |
dc.subject | s learning | - |
dc.subject | genetic algorithms | - |
dc.subject | co-adaptation | - |
dc.subject | VECTOR QUANTIZATION | - |
dc.subject | ALGORITHMS | - |
dc.subject | DESIGN | - |
dc.title | Co-adaptation of self-organizing maps by evolution and learning | - |
dc.type | Article | - |
dc.contributor.college | 컴퓨터공학과 | - |
dc.identifier.doi | 10.1016/S0925-2312(99)00129-0 | - |
dc.author.google | Kim, D | - |
dc.author.google | Ahn, S | - |
dc.author.google | Kang, DS | - |
dc.relation.volume | 30 | - |
dc.relation.issue | 1-4 | - |
dc.relation.startpage | 249 | - |
dc.relation.lastpage | 272 | - |
dc.contributor.id | 10054411 | - |
dc.relation.journal | NeuroComputing | - |
dc.relation.index | SCI급, SCOPUS 등재논문 | - |
dc.relation.sci | SCI | - |
dc.collections.name | Journal Papers | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | NeuroComputing, v.30, no.1-4, pp.249 - 272 | - |
dc.identifier.wosid | 000084063300023 | - |
dc.date.tcdate | 2018-03-23 | - |
dc.citation.endPage | 272 | - |
dc.citation.number | 1-4 | - |
dc.citation.startPage | 249 | - |
dc.citation.title | NeuroComputing | - |
dc.citation.volume | 30 | - |
dc.contributor.affiliatedAuthor | Kim, D | - |
dc.identifier.scopusid | 2-s2.0-0033991980 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.scptc | 0 | * |
dc.date.scptcdate | 2018-05-121 | * |
dc.type.docType | Article | - |
dc.subject.keywordPlus | VECTOR QUANTIZATION | - |
dc.subject.keywordPlus | ALGORITHMS | - |
dc.subject.keywordPlus | DESIGN | - |
dc.subject.keywordAuthor | self-organizing map | - |
dc.subject.keywordAuthor | vector quantization | - |
dc.subject.keywordAuthor | Kohonen&apos | - |
dc.subject.keywordAuthor | s learning | - |
dc.subject.keywordAuthor | genetic algorithms | - |
dc.subject.keywordAuthor | co-adaptation | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.