WEKO3
アイテム
{"_buckets": {"deposit": "637b4928-785d-4de6-9f24-8fbf78d00cca"}, "_deposit": {"created_by": 13, "id": "4975", "owners": [13], "pid": {"revision_id": 0, "type": "depid", "value": "4975"}, "status": "published"}, "_oai": {"id": "oai:mie-u.repo.nii.ac.jp:00004975", "sets": ["387"]}, "author_link": ["35375"], "item_4_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "1994-12-21", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "143", "bibliographicPageStart": "133", "bibliographicVolumeNumber": "19", "bibliographic_titles": [{"bibliographic_title": "Research reports of the Faculty of Engineering, Mie University"}]}]}, "item_4_description_14": {"attribute_name": "フォーマット", "attribute_value_mlt": [{"subitem_description": "application/pdf", "subitem_description_type": "Other"}]}, "item_4_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "A sigmoid function has been utilized for the input/output functions of the back-propagation type neural networks. It, however, has a local minimum problem ; if the output of the sigmoid function becomes 0 or 1, no further learning occurs even if there are errors between teaching inputs and outputs of the output unit. The offset method of applying some offset values to the intermediate layer cells is thought to be effective in solving the local minimum problem. In this paper, we propose two formulations of offset function ; the linearly decremental offset function that decrements offset values as iteration of the learning process increases, and the logarithmic error offset function that various offset values according as logarithm of output errors. The performance of these methods are evaluated by recognition test of handwriting.", "subitem_description_type": "Abstract"}]}, "item_4_publisher_30": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "Faculty of Engineering, Mie University"}]}, "item_4_source_id_7": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "0385-6208", "subitem_source_identifier_type": "PISSN"}]}, "item_4_source_id_9": {"attribute_name": "書誌レコードID", "attribute_value_mlt": [{"subitem_source_identifier": "AA00816341", "subitem_source_identifier_type": "NCID"}]}, "item_4_text_18": {"attribute_name": "その他のタイトル", "attribute_value_mlt": [{"subitem_text_language": "ja", "subitem_text_value": "可変オフセット法によるニューラルネット入出力関数の制御"}]}, "item_4_text_65": {"attribute_name": "資源タイプ(三重大)", "attribute_value_mlt": [{"subitem_text_value": "Departmental Bulletin Paper / 紀要論文"}]}, "item_access_right": {"attribute_name": "アクセス権", "attribute_value_mlt": [{"subitem_access_right": "metadata only access", "subitem_access_right_uri": "http://purl.org/coar/access_right/c_14cb"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Uda, Noriyuki", "creatorNameLang": "en"}, {"creatorName": "宇田, 紀之", "creatorNameLang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "35375", "nameIdentifierScheme": "WEKO"}]}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Neural networks", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Back-propagation", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Learning algorithm", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Offset values", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Recofnition of handwriting", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Local minimum problem", "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": "departmental bulletin paper", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Controlling the Input/Output Function of the Neural Network by Variable Offset Rule", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Controlling the Input/Output Function of the Neural Network by Variable Offset Rule", "subitem_title_language": "en"}]}, "item_type_id": "4", "owner": "13", "path": ["387"], "permalink_uri": "http://hdl.handle.net/10076/4007", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2018-03-15"}, "publish_date": "2018-03-15", "publish_status": "0", "recid": "4975", "relation": {}, "relation_version_is_last": true, "title": ["Controlling the Input/Output Function of the Neural Network by Variable Offset Rule"], "weko_shared_id": -1}
Controlling the Input/Output Function of the Neural Network by Variable Offset Rule
http://hdl.handle.net/10076/4007
http://hdl.handle.net/10076/4007a329c721-3e98-4427-acbe-4edccae33cd0
Item type | 紀要論文 / Departmental Bulletin Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2018-03-15 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Controlling the Input/Output Function of the Neural Network by Variable Offset Rule | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Neural networks | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Back-propagation | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Learning algorithm | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Offset values | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Recofnition of handwriting | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Local minimum problem | |||||
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 | departmental bulletin paper | |||||
アクセス権 | ||||||
アクセス権 | metadata only access | |||||
アクセス権URI | http://purl.org/coar/access_right/c_14cb | |||||
著者 |
宇田, 紀之
× 宇田, 紀之 |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | A sigmoid function has been utilized for the input/output functions of the back-propagation type neural networks. It, however, has a local minimum problem ; if the output of the sigmoid function becomes 0 or 1, no further learning occurs even if there are errors between teaching inputs and outputs of the output unit. The offset method of applying some offset values to the intermediate layer cells is thought to be effective in solving the local minimum problem. In this paper, we propose two formulations of offset function ; the linearly decremental offset function that decrements offset values as iteration of the learning process increases, and the logarithmic error offset function that various offset values according as logarithm of output errors. The performance of these methods are evaluated by recognition test of handwriting. | |||||
書誌情報 |
Research reports of the Faculty of Engineering, Mie University 巻 19, p. 133-143, 発行日 1994-12-21 |
|||||
ISSN | ||||||
収録物識別子タイプ | PISSN | |||||
収録物識別子 | 0385-6208 | |||||
書誌レコードID | ||||||
収録物識別子タイプ | NCID | |||||
収録物識別子 | AA00816341 | |||||
フォーマット | ||||||
内容記述タイプ | Other | |||||
内容記述 | application/pdf | |||||
その他のタイトル | ||||||
ja | ||||||
可変オフセット法によるニューラルネット入出力関数の制御 | ||||||
出版者 | ||||||
出版者 | Faculty of Engineering, Mie University | |||||
資源タイプ(三重大) | ||||||
Departmental Bulletin Paper / 紀要論文 |