Index Link

  • RootNode

Item

{"_buckets": {"deposit": "33d86f80-427d-425b-a064-47c61f43ac19"}, "_deposit": {"id": "4870", "owners": [], "pid": {"revision_id": 0, "type": "recid", "value": "4870"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/4870", "sets": ["1597824273898", "user-ucsy"]}, "communities": ["ucsy"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Performance analysis of q-valued dimensions Parametric Vector Neural Network classifier", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "Neural network ensemble techniques havebeen shown to be very accurate classificationtechniques. However, in some real-life applications,a number of classifiers required to achieve areasonable accuracy is enormously large and hencevery space consuming. This paper introduces specialneural method, Parametric Vector Neural Network(VNN), which has great associative memory and highperformance. Parametric VNN analyzed usingvarious size of database having randomly createdpatterns, noise levels, and fixed q-dimensions. Theresult shows that it has capacity much greater thanconventional Neural Networks. Once T matrix iscreated for the stored patterns in Database, mostsimilar pattern with the input one can be achievedeasily by just multiplying two matrices. The resultingassociative memory can recognize highly noisy andcorrelate input patterns."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "Vector Neural Network(VNN)"}, {"interim": "q- valued dimensions"}, {"interim": "Neural Network Classifier"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2019-07-11"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "proceeding_total-pages-288-292.pdf", "filesize": [{"value": "3228 Kb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 3228000.0, "url": {"url": "https://meral.edu.mm/record/4870/files/proceeding_total-pages-288-292.pdf"}, "version_id": "b33b465d-bcbc-4326-9290-903d014e0a5b"}]}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_issue": "", "subitem_journal_title": "Fifteenth International Conference on Computer Applications(ICCA 2017)", "subitem_pages": "", "subitem_volume": ""}]}, "item_1583103147082": {"attribute_name": "Conference papers", "attribute_value_mlt": [{"subitem_acronym": "", "subitem_c_date": "", "subitem_conference_title": "", "subitem_part": "", "subitem_place": "", "subitem_session": "", "subitem_website": ""}]}, "item_1583103211336": {"attribute_name": "Books/reports/chapters", "attribute_value_mlt": [{"subitem_book_title": "", "subitem_isbn": "", "subitem_pages": "", "subitem_place": "", "subitem_publisher": ""}]}, "item_1583103233624": {"attribute_name": "Thesis/dissertations", "attribute_value_mlt": [{"subitem_awarding_university": "", "subitem_supervisor(s)": [{"subitem_supervisor": ""}]}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "Soe, Nwe Nwe"}, {"subitem_authors_fullname": "Htay, Win"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Article"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2017-02-16"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "http://onlineresource.ucsy.edu.mm/handle/123456789/766"}, "item_title": "Performance analysis of q-valued dimensions Parametric Vector Neural Network classifier", "item_type_id": "21", "owner": "1", "path": ["1597824273898"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000004870", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2019-07-11"}, "publish_date": "2019-07-11", "publish_status": "0", "recid": "4870", "relation": {}, "relation_version_is_last": true, "title": ["Performance analysis of q-valued dimensions Parametric Vector Neural Network classifier"], "weko_shared_id": -1}

Performance analysis of q-valued dimensions Parametric Vector Neural Network classifier

http://hdl.handle.net/20.500.12678/0000004870
1b859ce2-75d8-4eae-8f05-b2814a8cd457
33d86f80-427d-425b-a064-47c61f43ac19
None
Name / File License Actions
proceeding_total-pages-288-292.pdf proceeding_total-pages-288-292.pdf (3228 Kb)
Publication type
Article
Upload type
Publication
Title
Title Performance analysis of q-valued dimensions Parametric Vector Neural Network classifier
Language en
Publication date 2017-02-16
Authors
Soe, Nwe Nwe
Htay, Win
Description
Neural network ensemble techniques havebeen shown to be very accurate classificationtechniques. However, in some real-life applications,a number of classifiers required to achieve areasonable accuracy is enormously large and hencevery space consuming. This paper introduces specialneural method, Parametric Vector Neural Network(VNN), which has great associative memory and highperformance. Parametric VNN analyzed usingvarious size of database having randomly createdpatterns, noise levels, and fixed q-dimensions. Theresult shows that it has capacity much greater thanconventional Neural Networks. Once T matrix iscreated for the stored patterns in Database, mostsimilar pattern with the input one can be achievedeasily by just multiplying two matrices. The resultingassociative memory can recognize highly noisy andcorrelate input patterns.
Keywords
Vector Neural Network(VNN), q- valued dimensions, Neural Network Classifier
Identifier http://onlineresource.ucsy.edu.mm/handle/123456789/766
Journal articles
Fifteenth International Conference on Computer Applications(ICCA 2017)
Conference papers
Books/reports/chapters
Thesis/dissertations
0
0
views
downloads
Views Downloads

Export

OAI-PMH
  • OAI-PMH DublinCore
Other Formats