WEKO3
インデックスリンク
アイテム
{"_buckets": {"deposit": "1077d3bc-c0e4-47ea-bede-35e8d0f7ee9f"}, "_deposit": {"created_by": 3, "id": "7600", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "7600"}, "status": "published"}, "_oai": {"id": "oai:kanazawa-u.repo.nii.ac.jp:00007600", "sets": ["936"]}, "author_link": ["353", "10171", "10172"], "item_8_biblio_info_8": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "1993-10-01", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "2606", "bibliographicPageStart": "2603", "bibliographicVolumeNumber": "3", "bibliographic_titles": [{"bibliographic_title": "Proceedings of the International Joint Conference on Neural Mateworks"}]}]}, "item_8_description_21": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Authors have proposed an asymmetrical associative neural network (NN) using variable hysteresis threshold and its learning and association algorithms. It can drastically improve noise performance, that is insensitivity to noise. In this paper, memory capacity bound and threshold optimization in this associative NN are further discussed. Binary random patterns are considered. First, relation between the number of patterns and the number of iterations is investigated. The latter gradually increases until some number of patterns. After that, it suddenly increases. This is a very peculiar phenomenon. This turning point gives the memory capacity bound, that is about 1.56N, where N is the number of units. Next, threshold optimization is discussed. Relation between threshold and noise performance, and effects of connection weight distribution on noise performance are theoretically discussed. Based on these results, a ratio of step-size and the threshold is optimized to be 0.5/(NP-1), where NP is the number of units on the pattern. Numerically statistical simulation demonstrates efficiency of the proposed methods.", "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": "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": "10171", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Katayama, Hiroshi"}], "nameIdentifiers": [{"nameIdentifier": "10172", "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-2603.pdf", "filesize": [{"value": "238.9 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 238900.0, "url": {"label": "TE-PR-NAKAYAMA-K-2603.pdf", "url": "https://kanazawa-u.repo.nii.ac.jp/record/7600/files/TE-PR-NAKAYAMA-K-2603.pdf"}, "version_id": "0a8bcbd2-6031-405f-b471-acf6538edf22"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Recurrent neural networks", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Threshold optimization", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Variable synthesis threshold", "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": "Memory capacity bound and threshold optimization in recurrent neural network with variable hysteresis threshold", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Memory capacity bound and threshold optimization in recurrent neural network with variable hysteresis threshold"}]}, "item_type_id": "8", "owner": "3", "path": ["936"], "permalink_uri": "http://hdl.handle.net/2297/6797", "pubdate": {"attribute_name": "公開日", "attribute_value": "2017-10-03"}, "publish_date": "2017-10-03", "publish_status": "0", "recid": "7600", "relation": {}, "relation_version_is_last": true, "title": ["Memory capacity bound and threshold optimization in recurrent neural network with variable hysteresis threshold"], "weko_shared_id": -1}
Memory capacity bound and threshold optimization in recurrent neural network with variable hysteresis threshold
http://hdl.handle.net/2297/6797
http://hdl.handle.net/2297/6797d71a6739-25bc-4494-aaa0-c146f82cd277
名前 / ファイル | ライセンス | アクション |
---|---|---|
TE-PR-NAKAYAMA-K-2603.pdf (238.9 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 | Memory capacity bound and threshold optimization in recurrent neural network with variable hysteresis threshold | |||||
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× Katayama, Hiroshi |
|||||
書誌情報 |
Proceedings of the International Joint Conference on Neural Mateworks 巻 3, p. 2603-2606, 発行日 1993-10-01 |
|||||
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 | Authors have proposed an asymmetrical associative neural network (NN) using variable hysteresis threshold and its learning and association algorithms. It can drastically improve noise performance, that is insensitivity to noise. In this paper, memory capacity bound and threshold optimization in this associative NN are further discussed. Binary random patterns are considered. First, relation between the number of patterns and the number of iterations is investigated. The latter gradually increases until some number of patterns. After that, it suddenly increases. This is a very peculiar phenomenon. This turning point gives the memory capacity bound, that is about 1.56N, where N is the number of units. Next, threshold optimization is discussed. Relation between threshold and noise performance, and effects of connection weight distribution on noise performance are theoretically discussed. Based on these results, a ratio of step-size and the threshold is optimized to be 0.5/(NP-1), where NP is the number of units on the pattern. Numerically statistical simulation demonstrates efficiency of the proposed methods. | |||||
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 |