WEKO3
インデックスリンク
アイテム
{"_buckets": {"deposit": "1e4babfb-08fc-4eee-abab-fdb6c6ae052d"}, "_deposit": {"created_by": 3, "id": "7643", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "7643"}, "status": "published"}, "_oai": {"id": "oai:kanazawa-u.repo.nii.ac.jp:00007643", "sets": ["936"]}, "author_link": ["353", "10259", "10258"], "item_8_biblio_info_8": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "1999-07-01", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "1656", "bibliographicPageStart": "1652", "bibliographicVolumeNumber": "3", "bibliographic_titles": [{"bibliographic_title": "Proceedings of the International Joint Conference on Neural Networks"}]}]}, "item_8_description_21": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "A method has been proposed for weight initialization in back-propagation feed-forward networks. Training data is analyzed and the notion of critical point is introduced for determining the initial weights and the number of hidden units. The proposed method has been applied to artificial data and the publicly available cancer database. The experimental results of artificial data show that the proposed method takes 1/3 of the training time required for standard back-propagation. In order to verify the effectiveness of the proposed method, standard back-propagation, where the learning starts with random initial weights was also applied to the cancer database. The experimental results indicate that the proposed weight initialization method results in better generalization.", "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_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": "Keeni, Kanad"}], "nameIdentifiers": [{"nameIdentifier": "10258", "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"}]}, {"creatorNames": [{"creatorName": "Shimodaira, Hiroshi"}], "nameIdentifiers": [{"nameIdentifier": "10259", "nameIdentifierScheme": "WEKO"}]}]}, "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-1652.pdf", "filesize": [{"value": "435.0 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 435000.0, "url": {"label": "TE-PR-NAKAYAMA-K-1652.pdf", "url": "https://kanazawa-u.repo.nii.ac.jp/record/7643/files/TE-PR-NAKAYAMA-K-1652.pdf"}, "version_id": "a2dee723-3481-49dd-9eb3-d29c3ca5a118"}]}, "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": "Estimation of initial weights and hidden units for fast learning of multi-layer neural networks for pattern classification", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Estimation of initial weights and hidden units for fast learning of multi-layer neural networks for pattern classification"}]}, "item_type_id": "8", "owner": "3", "path": ["936"], "permalink_uri": "http://hdl.handle.net/2297/6800", "pubdate": {"attribute_name": "公開日", "attribute_value": "2017-10-03"}, "publish_date": "2017-10-03", "publish_status": "0", "recid": "7643", "relation": {}, "relation_version_is_last": true, "title": ["Estimation of initial weights and hidden units for fast learning of multi-layer neural networks for pattern classification"], "weko_shared_id": -1}
Estimation of initial weights and hidden units for fast learning of multi-layer neural networks for pattern classification
http://hdl.handle.net/2297/6800
http://hdl.handle.net/2297/6800c1b47afe-3886-42df-a42b-22db19e3344a
名前 / ファイル | ライセンス | アクション |
---|---|---|
TE-PR-NAKAYAMA-K-1652.pdf (435.0 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 | Estimation of initial weights and hidden units for fast learning of multi-layer neural networks for pattern classification | |||||
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 |
Keeni, Kanad
× Keeni, Kanad× Nakayama, Kenji× Shimodaira, Hiroshi |
|||||
書誌情報 |
Proceedings of the International Joint Conference on Neural Networks 巻 3, p. 1652-1656, 発行日 1999-07-01 |
|||||
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 | A method has been proposed for weight initialization in back-propagation feed-forward networks. Training data is analyzed and the notion of critical point is introduced for determining the initial weights and the number of hidden units. The proposed method has been applied to artificial data and the publicly available cancer database. The experimental results of artificial data show that the proposed method takes 1/3 of the training time required for standard back-propagation. In order to verify the effectiveness of the proposed method, standard back-propagation, where the learning starts with random initial weights was also applied to the cancer database. The experimental results indicate that the proposed weight initialization method results in better generalization. | |||||
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 |