WEKO3
アイテム
{"_buckets": {"deposit": "0651bb1d-0aae-4b5f-bcbe-2f31e8e19698"}, "_deposit": {"created_by": 27, "id": "449", "owners": [27], "pid": {"revision_id": 0, "type": "depid", "value": "449"}, "status": "published"}, "_oai": {"id": "oai:oist.repo.nii.ac.jp:00000449", "sets": ["78"]}, "author_link": ["1860", "1861"], "item_10001_biblio_info_7": {"attribute_name": "Bibliographic Information", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2017-03-21", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "16", "bibliographicPageStart": "3", "bibliographicVolumeNumber": "92", "bibliographic_titles": [{}, {"bibliographic_title": "Neural Networks", "bibliographic_titleLang": "en"}]}]}, "item_10001_creator_3": {"attribute_name": "Author", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Ahmadi, Ahmadreza"}], "nameIdentifiers": [{"nameIdentifier": "1860", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Tani, Jun"}], "nameIdentifiers": [{"nameIdentifier": "1861", "nameIdentifierScheme": "WEKO"}]}]}, "item_10001_description_5": {"attribute_name": "Abstract", "attribute_value_mlt": [{"subitem_description": "The current paper examines how a recurrent neural network (RNN) model using a dynamic predictive coding scheme can cope with fluctuations in temporal patterns through generalization in learning. The conjecture driving this present inquiry is that a RNN model with multiple timescales (MTRNN) learns by extracting patterns of change from observed temporal patterns, developing an internal dynamic structure such that variance in initial internal states account for modulations in corresponding observed patterns. We trained a MTRNN with low-dimensional temporal patterns, and assessed performance on an imitation task employing these patterns. Analysis reveals that imitating fluctuated patterns consists in inferring optimal internal states by error regression. The model was then tested through humanoid robotic experiments requiring imitative interaction with human subjects. Results show that spontaneous and lively interaction can be achieved as the model successfully copes with fluctuations naturally occurring in human movement patterns.", "subitem_description_type": "Other"}]}, "item_10001_publisher_8": {"attribute_name": "Publisher", "attribute_value_mlt": [{"subitem_publisher": "Elsevier Ltd."}]}, "item_10001_relation_13": {"attribute_name": "PubMedNo.", "attribute_value_mlt": [{"subitem_relation_type": "isVersionOf", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:pmid/28385623", "subitem_relation_type_select": "PMID"}}]}, "item_10001_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isVersionOf", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:doi/10.1016/j.neunet.2017.02.015", "subitem_relation_type_select": "DOI"}}]}, "item_10001_relation_17": {"attribute_name": "Related site", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://www.sciencedirect.com/science/article/pii/S0893608017300618", "subitem_relation_type_select": "URI"}}]}, "item_10001_rights_15": {"attribute_name": "Rights", "attribute_value_mlt": [{"subitem_rights": "© 2017 Elsevier Ltd."}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "0893-6080", "subitem_source_identifier_type": "ISSN"}]}, "item_10001_version_type_20": {"attribute_name": "Author\u0027s flag", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_ab4af688f83e57aa", "subitem_version_type": "AM"}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2019-03-22"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "Accepted-Paper-NN.pdf", "filesize": [{"value": "4.6 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International\nhttps://creativecommons.org/licenses/by-nc-nd/4.0/", "licensetype": "license_free", "mimetype": "application/pdf", "size": 4600000.0, "url": {"label": "Accepted-Paper-NN", "url": "https://oist.repo.nii.ac.jp/record/449/files/Accepted-Paper-NN.pdf"}, "version_id": "951f9d03-30da-4a6f-a492-23c398eb1837"}]}, "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": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "How can a recurrent neurodynamic predictive coding model cope with fluctuation in temporal patterns? Robotic experiments on imitative interaction", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "How can a recurrent neurodynamic predictive coding model cope with fluctuation in temporal patterns? Robotic experiments on imitative interaction", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "27", "path": ["78"], "permalink_uri": "https://oist.repo.nii.ac.jp/records/449", "pubdate": {"attribute_name": "公開日", "attribute_value": "2019-03-22"}, "publish_date": "2019-03-22", "publish_status": "0", "recid": "449", "relation": {}, "relation_version_is_last": true, "title": ["How can a recurrent neurodynamic predictive coding model cope with fluctuation in temporal patterns? Robotic experiments on imitative interaction"], "weko_shared_id": 27}
How can a recurrent neurodynamic predictive coding model cope with fluctuation in temporal patterns? Robotic experiments on imitative interaction
https://oist.repo.nii.ac.jp/records/449
https://oist.repo.nii.ac.jp/records/44975aea9c8-0b19-4149-8cf7-2008253f8ec9
名前 / ファイル | ライセンス | アクション |
---|---|---|
Accepted-Paper-NN (4.6 MB)
|
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
https://creativecommons.org/licenses/by-nc-nd/4.0/ |
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2019-03-22 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | How can a recurrent neurodynamic predictive coding model cope with fluctuation in temporal patterns? Robotic experiments on imitative interaction | |||||
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_6501 | |||||
資源タイプ | journal article | |||||
著者(英) |
Ahmadi, Ahmadreza
× Ahmadi, Ahmadreza× Tani, Jun |
|||||
書誌情報 |
en : Neural Networks 巻 92, p. 3-16, 発行日 2017-03-21 |
|||||
抄録 | ||||||
内容記述タイプ | Other | |||||
内容記述 | The current paper examines how a recurrent neural network (RNN) model using a dynamic predictive coding scheme can cope with fluctuations in temporal patterns through generalization in learning. The conjecture driving this present inquiry is that a RNN model with multiple timescales (MTRNN) learns by extracting patterns of change from observed temporal patterns, developing an internal dynamic structure such that variance in initial internal states account for modulations in corresponding observed patterns. We trained a MTRNN with low-dimensional temporal patterns, and assessed performance on an imitation task employing these patterns. Analysis reveals that imitating fluctuated patterns consists in inferring optimal internal states by error regression. The model was then tested through humanoid robotic experiments requiring imitative interaction with human subjects. Results show that spontaneous and lively interaction can be achieved as the model successfully copes with fluctuations naturally occurring in human movement patterns. | |||||
出版者 | ||||||
出版者 | Elsevier Ltd. | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 0893-6080 | |||||
PubMed番号 | ||||||
関連タイプ | isVersionOf | |||||
識別子タイプ | PMID | |||||
関連識別子 | info:pmid/28385623 | |||||
DOI | ||||||
関連タイプ | isVersionOf | |||||
識別子タイプ | DOI | |||||
関連識別子 | info:doi/10.1016/j.neunet.2017.02.015 | |||||
権利 | ||||||
権利情報 | © 2017 Elsevier Ltd. | |||||
関連サイト | ||||||
識別子タイプ | URI | |||||
関連識別子 | https://www.sciencedirect.com/science/article/pii/S0893608017300618 | |||||
著者版フラグ | ||||||
出版タイプ | AM | |||||
出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa |