WEKO3
インデックスリンク
アイテム
{"_buckets": {"deposit": "002b55d0-b7f1-499b-9459-9914b9f34be2"}, "_deposit": {"created_by": 3, "id": "7375", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "7375"}, "status": "published"}, "_oai": {"id": "oai:kanazawa-u.repo.nii.ac.jp:00007375", "sets": ["936"]}, "author_link": ["353", "9719"], "item_4_biblio_info_8": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "1998-03-01", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "3", "bibliographicPageEnd": "381", "bibliographicPageStart": "374", "bibliographicVolumeNumber": "E81-A", "bibliographic_titles": [{"bibliographic_title": "IEICE Trans. Fundamentals"}]}]}, "item_4_description_21": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "A training data selection method is proposed for multilayer neural networks (MLNNs). This method selects a small number of the training data, which guarantee both generalization and fast training of the MLNNs applied to pattern classification. The generalization will be satisfied using the data locate close to the boundary of the pattern classes. However, if these data are only used in the training, convergence is slow. This phenomenon is analyzed in this paper. Therefore, in the proposed method, the MLNN is first trained using some number of the data, which are randomly selected (Step 1). The data, for which the output error is relatively large, are selected. Furthermore, they are paired with the nearest data belong to the different class. The newly selected data are further paired with the nearest data. Finally, pairs of the data, which locate close to the boundary, can be found. Using these pairs of the data, the MLNNs are further trained (Step 2). Since, there are some variations to combine Steps 1 and 2, the proposed method can be applied to both off-line and on-line training. The proposed method can reduce the number of the training data, at the same time, can hasten the training. Usefulness is confirmed through computer simulation.", "subitem_description_type": "Abstract"}]}, "item_4_description_5": {"attribute_name": "提供者所属", "attribute_value_mlt": [{"subitem_description": "金沢大学大学院自然科学研究科知能情報・数理", "subitem_description_type": "Other"}]}, "item_4_rights_23": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "(社)電子情報通信学会の許諾を得て登録"}]}, "item_4_source_id_11": {"attribute_name": "NCID", "attribute_value_mlt": [{"subitem_source_identifier": "AA0086650X", "subitem_source_identifier_type": "NCID"}]}, "item_4_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "0916-8508", "subitem_source_identifier_type": "ISSN"}]}, "item_4_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": "Hara, Kazuyuki"}], "nameIdentifiers": [{"nameIdentifier": "9719", "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-374.pdf", "filesize": [{"value": "657.2 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 657200.0, "url": {"label": "TE-PR-NAKAYAMA-K-374.pdf", "url": "https://kanazawa-u.repo.nii.ac.jp/record/7375/files/TE-PR-NAKAYAMA-K-374.pdf"}, "version_id": "071f8ab1-4fb1-4b3c-8581-41b177dee2b8"}]}, "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": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Training data selection method for generalization by multilayer neural networks", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Training data selection method for generalization by multilayer neural networks"}]}, "item_type_id": "4", "owner": "3", "path": ["936"], "permalink_uri": "http://hdl.handle.net/2297/5654", "pubdate": {"attribute_name": "公開日", "attribute_value": "2017-10-03"}, "publish_date": "2017-10-03", "publish_status": "0", "recid": "7375", "relation": {}, "relation_version_is_last": true, "title": ["Training data selection method for generalization by multilayer neural networks"], "weko_shared_id": 3}
Training data selection method for generalization by multilayer neural networks
http://hdl.handle.net/2297/5654
http://hdl.handle.net/2297/56548882ea61-93b9-402c-99fc-ad61a44e06c7
名前 / ファイル | ライセンス | アクション |
---|---|---|
TE-PR-NAKAYAMA-K-374.pdf (657.2 kB)
|
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2017-10-03 | |||||
タイトル | ||||||
タイトル | Training data selection method for generalization by multilayer neural networks | |||||
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_6501 | |||||
資源タイプ | journal article | |||||
著者 |
Hara, Kazuyuki
× Hara, Kazuyuki× Nakayama, Kenji |
|||||
提供者所属 | ||||||
内容記述タイプ | Other | |||||
内容記述 | 金沢大学大学院自然科学研究科知能情報・数理 | |||||
書誌情報 |
IEICE Trans. Fundamentals 巻 E81-A, 号 3, p. 374-381, 発行日 1998-03-01 |
|||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 0916-8508 | |||||
NCID | ||||||
収録物識別子タイプ | NCID | |||||
収録物識別子 | AA0086650X | |||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | A training data selection method is proposed for multilayer neural networks (MLNNs). This method selects a small number of the training data, which guarantee both generalization and fast training of the MLNNs applied to pattern classification. The generalization will be satisfied using the data locate close to the boundary of the pattern classes. However, if these data are only used in the training, convergence is slow. This phenomenon is analyzed in this paper. Therefore, in the proposed method, the MLNN is first trained using some number of the data, which are randomly selected (Step 1). The data, for which the output error is relatively large, are selected. Furthermore, they are paired with the nearest data belong to the different class. The newly selected data are further paired with the nearest data. Finally, pairs of the data, which locate close to the boundary, can be found. Using these pairs of the data, the MLNNs are further trained (Step 2). Since, there are some variations to combine Steps 1 and 2, the proposed method can be applied to both off-line and on-line training. The proposed method can reduce the number of the training data, at the same time, can hasten the training. Usefulness is confirmed through computer simulation. | |||||
権利 | ||||||
権利情報 | (社)電子情報通信学会の許諾を得て登録 | |||||
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 |