WEKO3
アイテム
{"_buckets": {"deposit": "e4d08d69-4b80-49c1-bf99-8d759c28f5d4"}, "_deposit": {"created_by": 7, "id": "1443", "owners": [7], "pid": {"revision_id": 0, "type": "depid", "value": "1443"}, "status": "published"}, "_oai": {"id": "oai:pu-hiroshima.repo.nii.ac.jp:00001443", "sets": ["137"]}, "author_link": ["3009", "3008"], "item_10003_biblio_info_7": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2018", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "76", "bibliographicPageStart": "70", "bibliographic_titles": [{"bibliographic_title": "2018 IEEE SMC Hiroshima Chapter若手研究会講演論文集"}]}]}, "item_10003_description_19": {"attribute_name": "フォーマット", "attribute_value_mlt": [{"subitem_description": "application/pdf", "subitem_description_type": "Other"}]}, "item_10003_description_5": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Abstract?Deep Learning has a hierarchical network architecture to represent the complicated feature of in-put patterns. We have developed the adaptive structure learning method of Deep Belief Network (DBN) that can discover an optimal number of hidden neurons for given input data in a Restricted Boltzmann Machine (RBM)by neuron generation-annihilation algorithm, and hidden layers in DBN. The knowledge extraction method from the developed DBN and the recti?cation method of the signal ?ow on the wrong path have been developed. The ?ne-tuning method can reach an incredible high accuracy of classi?cation (the best record). In Deep Learning, the layer-wise unsupervised pre-training can construct abstract and concrete modes of information processing. In this paper we improve the knowledge acquisition method to adopt a distinction between abstract and concrete. The empirical study was executed on the ChestX-ray8 database.", "subitem_description_language": "en", "subitem_description_type": "Abstract"}]}, "item_10003_description_6": {"attribute_name": "内容記述", "attribute_value_mlt": [{"subitem_description": "開催日:平成30年7月28日 会場:広島工業大学", "subitem_description_type": "Other"}]}, "item_10003_publisher_8": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "IEEE SMC Hiroshima Chapter"}]}, "item_10003_version_type_20": {"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": "市村, 匠", "creatorNameLang": "ja"}, {"creatorName": "イチムラ, タクミ", "creatorNameLang": "ja-Kana"}, {"creatorName": "ICHIMURA, Takumi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "3009", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "鎌田, 真", "creatorNameLang": "ja"}, {"creatorName": "カマダ, シン", "creatorNameLang": "ja-Kana"}, {"creatorName": "KAMADA, Shin", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "3008", "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": "2023-04-18"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "IchimuraT070.pdf", "filesize": [{"value": "378.5 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_note", "mimetype": "application/pdf", "size": 378500.0, "url": {"label": "IchimuraT070.pdf", "url": "https://pu-hiroshima.repo.nii.ac.jp/record/1443/files/IchimuraT070.pdf"}, "version_id": "d74c4f72-f9c0-4e69-b4e3-e7d874dcb87c"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "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": "構造適応型Deep Belief Network事前学習を考慮した知識獲得の検討", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "構造適応型Deep Belief Network事前学習を考慮した知識獲得の検討", "subitem_title_language": "ja"}, {"subitem_title": "Knowledge Acquisition in Consideration of Pre-training for Adaptive Structural Learning of Deep Belief Network", "subitem_title_language": "en"}]}, "item_type_id": "10003", "owner": "7", "path": ["137"], "permalink_uri": "https://pu-hiroshima.repo.nii.ac.jp/records/1443", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2023-04-18"}, "publish_date": "2023-04-18", "publish_status": "0", "recid": "1443", "relation": {}, "relation_version_is_last": true, "title": ["構造適応型Deep Belief Network事前学習を考慮した知識獲得の検討"], "weko_shared_id": -1}
構造適応型Deep Belief Network事前学習を考慮した知識獲得の検討
https://pu-hiroshima.repo.nii.ac.jp/records/1443
https://pu-hiroshima.repo.nii.ac.jp/records/1443acee23ed-a164-41c5-a0a6-a1f74e0a935a
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]() |
|
Item type | 会議発表論文 / Conference Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2023-04-18 | |||||
タイトル | ||||||
言語 | ja | |||||
タイトル | 構造適応型Deep Belief Network事前学習を考慮した知識獲得の検討 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Knowledge Acquisition in Consideration of Pre-training for Adaptive Structural Learning of Deep Belief Network | |||||
言語 | ||||||
言語 | jpn | |||||
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 |
市村, 匠
× 市村, 匠× 鎌田, 真 |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | Abstract?Deep Learning has a hierarchical network architecture to represent the complicated feature of in-put patterns. We have developed the adaptive structure learning method of Deep Belief Network (DBN) that can discover an optimal number of hidden neurons for given input data in a Restricted Boltzmann Machine (RBM)by neuron generation-annihilation algorithm, and hidden layers in DBN. The knowledge extraction method from the developed DBN and the recti?cation method of the signal ?ow on the wrong path have been developed. The ?ne-tuning method can reach an incredible high accuracy of classi?cation (the best record). In Deep Learning, the layer-wise unsupervised pre-training can construct abstract and concrete modes of information processing. In this paper we improve the knowledge acquisition method to adopt a distinction between abstract and concrete. The empirical study was executed on the ChestX-ray8 database. | |||||
言語 | en | |||||
内容記述 | ||||||
内容記述タイプ | Other | |||||
内容記述 | 開催日:平成30年7月28日 会場:広島工業大学 | |||||
書誌情報 |
2018 IEEE SMC Hiroshima Chapter若手研究会講演論文集 p. 70-76, 発行日 2018 |
|||||
出版者 | ||||||
出版者 | IEEE SMC Hiroshima Chapter | |||||
フォーマット | ||||||
内容記述タイプ | Other | |||||
内容記述 | application/pdf | |||||
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 |