WEKO3
インデックスリンク
アイテム
{"_buckets": {"deposit": "9a8275c5-73df-44b8-900b-a6af04c4347a"}, "_deposit": {"created_by": 3, "id": "7766", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "7766"}, "status": "published"}, "_oai": {"id": "oai:kanazawa-u.repo.nii.ac.jp:00007766", "sets": ["936"]}, "author_link": ["353", "10535"], "item_8_biblio_info_8": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "1994-06-01", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "1168", "bibliographicPageStart": "1163", "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": "An associative memory using fixed and variable hysteresis thresholds in learning and recalling processes, respectively, has been proposed by authors. This model can achieve a large memory capacity and very low noise sensitivity. However, a relation between weight change Δ w and the hysteresis threshold ± T has not been well discussed. In this paper, a new learning algorithm is proposed, which is based on a delta rule. However, in order to stabilize the learning process, a method of using double hysteresis thresholds is proposed. Unit states are updated using ± T. The error, used for adjusting weights, is evaluated using ± (T+dT). This means \u0027over correction\u0027. Stable and fast convergence can be obtained. Relations between η =dT/T and convergence rate and noise sensitivity are discussed, resulting the optimum selection for η. Furthermore, the order of presenting training data is optimized taking correlation, into account. In the recalling process, a threshold control method is further proposed in order to achieve fast recalling from noisy patterns.", "subitem_description_type": "Abstract"}]}, "item_8_description_5": {"attribute_name": "提供者所属", "attribute_value_mlt": [{"subitem_description": "金沢大学理工研究域電子情報学系", "subitem_description_type": "Other"}]}, "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": "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": "Nishimura, Katsuaki"}], "nameIdentifiers": [{"nameIdentifier": "10535", "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-1163.pdf", "filesize": [{"value": "790.6 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 790600.0, "url": {"label": "TE-PR-NAKAYAMA-K-1163.pdf", "url": "https://kanazawa-u.repo.nii.ac.jp/record/7766/files/TE-PR-NAKAYAMA-K-1163.pdf"}, "version_id": "7226f9d3-5a6e-4115-8d5c-e065573768ce"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Convergence of numerical methods", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Correlation methods; Mathematical models", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Neural networks", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Optimization", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Sensitivity analysis", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Spurious signal noise", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Stability", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Delta rule algorithm", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Double hysteresis thresholds", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Memory capacity", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Recurrent associative memory", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Associative storage", "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 delta rule algorithm using double hysteresis thresholds for recurrent associative memory", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "A delta rule algorithm using double hysteresis thresholds for recurrent associative memory"}]}, "item_type_id": "8", "owner": "3", "path": ["936"], "permalink_uri": "http://hdl.handle.net/2297/6853", "pubdate": {"attribute_name": "公開日", "attribute_value": "2017-10-03"}, "publish_date": "2017-10-03", "publish_status": "0", "recid": "7766", "relation": {}, "relation_version_is_last": true, "title": ["A delta rule algorithm using double hysteresis thresholds for recurrent associative memory"], "weko_shared_id": -1}
A delta rule algorithm using double hysteresis thresholds for recurrent associative memory
http://hdl.handle.net/2297/6853
http://hdl.handle.net/2297/6853c0b2d35c-fb91-454d-b696-96b161799b6d
名前 / ファイル | ライセンス | アクション |
---|---|---|
TE-PR-NAKAYAMA-K-1163.pdf (790.6 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 delta rule algorithm using double hysteresis thresholds for recurrent associative memory | |||||
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 |
Nakayama, Kenji
× Nakayama, Kenji× Nishimura, Katsuaki |
|||||
提供者所属 | ||||||
内容記述タイプ | Other | |||||
内容記述 | 金沢大学理工研究域電子情報学系 | |||||
書誌情報 |
IEEE International Conference on Neural Networks - Conference Proceedings p. 1163-1168, 発行日 1994-06-01 |
|||||
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 | An associative memory using fixed and variable hysteresis thresholds in learning and recalling processes, respectively, has been proposed by authors. This model can achieve a large memory capacity and very low noise sensitivity. However, a relation between weight change Δ w and the hysteresis threshold ± T has not been well discussed. In this paper, a new learning algorithm is proposed, which is based on a delta rule. However, in order to stabilize the learning process, a method of using double hysteresis thresholds is proposed. Unit states are updated using ± T. The error, used for adjusting weights, is evaluated using ± (T+dT). This means 'over correction'. Stable and fast convergence can be obtained. Relations between η =dT/T and convergence rate and noise sensitivity are discussed, resulting the optimum selection for η. Furthermore, the order of presenting training data is optimized taking correlation, into account. In the recalling process, a threshold control method is further proposed in order to achieve fast recalling from noisy patterns. | |||||
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 |