WEKO3
インデックスリンク
アイテム
{"_buckets": {"deposit": "3cb7f03f-438f-4c1d-a543-7d62c1a96ca1"}, "_deposit": {"created_by": 3, "id": "7424", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "7424"}, "status": "published"}, "_oai": {"id": "oai:kanazawa-u.repo.nii.ac.jp:00007424", "sets": ["936"]}, "author_link": ["353", "9824"], "item_8_biblio_info_8": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "1997-06-01", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "1918", "bibliographicPageStart": "1913", "bibliographicVolumeNumber": "3", "bibliographic_titles": [{"bibliographic_title": "IEEE International Conference on Neural Networks - Conference Proceedings"}]}]}, "item_8_description_21": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "In this paper, the geometric learning algorithm (GLA) is proposed for an elementary perceptron which includes a single output neuron. The GLA is a modified version of the affine projection algorithm (APA) for adaptive filters. The weights update vector is determined geometrically towards the intersection of the k hyperplanes which are perpendicular to patterns to be classified. k is the order of the GLA. In the case of the APA, the target of the coefficients update is a single point which corresponds to the best identification of the unknown system. On the other hand, in the case of the GLA, the target of the weights update is an area, in which all the given patterns are classified correctly. Thus, their convergence conditions are different. In this paper, the convergence condition of the 1st order GLA for 2 patterns is theoretically derived. The new concept `the angle of the solution area\u0027 is introduced. The computer simulation results support that this new concept is a good estimation of the convergence properties.", "subitem_description_type": "Abstract"}]}, "item_8_publisher_17": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "IEEE(Institute of Electrical and Electronics Engineers)"}]}, "item_8_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "1098-7576", "subitem_source_identifier_type": "ISSN"}]}, "item_8_version_type_25": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Miyoshi, Seiji"}], "nameIdentifiers": [{"nameIdentifier": "9824", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Nakayama, Kenji"}], "nameIdentifiers": [{"nameIdentifier": "353", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "00207945", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://kaken.nii.ac.jp/ja/search/?qm=00207945"}, {"nameIdentifier": "00207945", "nameIdentifierScheme": "研究者番号", "nameIdentifierURI": "https://nrid.nii.ac.jp/nrid/1000000207945"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2017-10-03"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "TE-PR-NAKAYAMA-K-1913.pdf", "filesize": [{"value": "796.8 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 796800.0, "url": {"label": "TE-PR-NAKAYAMA-K-1913.pdf", "url": "https://kanazawa-u.repo.nii.ac.jp/record/7424/files/TE-PR-NAKAYAMA-K-1913.pdf"}, "version_id": "c801593d-6f35-4b9f-9b16-8467b8947076"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Adaptive filtering", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Computer simulation", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Convergence of numerical methods", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Learning algorithms", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Learning systems", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Parameter estimation", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Pattern recognition", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Affine projection algorithms (APA)", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Geometric learning algorithms (GLA)", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Neural networks", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "conference paper", "resourceuri": "http://purl.org/coar/resource_type/c_5794"}]}, "item_title": "A geometric learning algorithm for elementary perceptron and its convergence analysis", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "A geometric learning algorithm for elementary perceptron and its convergence analysis"}]}, "item_type_id": "8", "owner": "3", "path": ["936"], "permalink_uri": "http://hdl.handle.net/2297/6848", "pubdate": {"attribute_name": "公開日", "attribute_value": "2017-10-03"}, "publish_date": "2017-10-03", "publish_status": "0", "recid": "7424", "relation": {}, "relation_version_is_last": true, "title": ["A geometric learning algorithm for elementary perceptron and its convergence analysis"], "weko_shared_id": -1}
A geometric learning algorithm for elementary perceptron and its convergence analysis
http://hdl.handle.net/2297/6848
http://hdl.handle.net/2297/68484befa906-8bad-4110-916e-20bc7f7d5195
名前 / ファイル | ライセンス | アクション |
---|---|---|
TE-PR-NAKAYAMA-K-1913.pdf (796.8 kB)
|
|
Item type | 会議発表論文 / Conference Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2017-10-03 | |||||
タイトル | ||||||
タイトル | A geometric learning algorithm for elementary perceptron and its convergence analysis | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||
資源タイプ | conference paper | |||||
著者 |
Miyoshi, Seiji
× Miyoshi, Seiji× Nakayama, Kenji |
|||||
書誌情報 |
IEEE International Conference on Neural Networks - Conference Proceedings 巻 3, p. 1913-1918, 発行日 1997-06-01 |
|||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 1098-7576 | |||||
出版者 | ||||||
出版者 | IEEE(Institute of Electrical and Electronics Engineers) | |||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | In this paper, the geometric learning algorithm (GLA) is proposed for an elementary perceptron which includes a single output neuron. The GLA is a modified version of the affine projection algorithm (APA) for adaptive filters. The weights update vector is determined geometrically towards the intersection of the k hyperplanes which are perpendicular to patterns to be classified. k is the order of the GLA. In the case of the APA, the target of the coefficients update is a single point which corresponds to the best identification of the unknown system. On the other hand, in the case of the GLA, the target of the weights update is an area, in which all the given patterns are classified correctly. Thus, their convergence conditions are different. In this paper, the convergence condition of the 1st order GLA for 2 patterns is theoretically derived. The new concept `the angle of the solution area' is introduced. The computer simulation results support that this new concept is a good estimation of the convergence properties. | |||||
著者版フラグ | ||||||
出版タイプ | VoR | |||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 |