WEKO3
アイテム
{"_buckets": {"deposit": "046da6ca-8479-4c69-830f-068cb7dc3ff4"}, "_deposit": {"created_by": 28, "id": "1104", "owners": [28], "pid": {"revision_id": 0, "type": "depid", "value": "1104"}, "status": "published"}, "_oai": {"id": "oai:oist.repo.nii.ac.jp:00001104", "sets": ["78"]}, "author_link": ["6149", "6146", "6148", "6150", "6147"], "item_10001_biblio_info_7": {"attribute_name": "Bibliographic Information", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2018-08-21", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "5", "bibliographicPageEnd": "1290", "bibliographicPageStart": "1271", "bibliographicVolumeNumber": "43", "bibliographic_titles": [{}, {"bibliographic_title": "Autonomous Robots", "bibliographic_titleLang": "en"}]}]}, "item_10001_creator_3": {"attribute_name": "Author", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Zhong, Junpei"}], "nameIdentifiers": [{"nameIdentifier": "6146", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Peniak, Martin"}], "nameIdentifiers": [{"nameIdentifier": "6147", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Tani, Jun"}], "nameIdentifiers": [{"nameIdentifier": "6148", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Ogata, Tetsuya"}], "nameIdentifiers": [{"nameIdentifier": "6149", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Cangelosi, Angelo"}], "nameIdentifiers": [{"nameIdentifier": "6150", "nameIdentifierScheme": "WEKO"}]}]}, "item_10001_description_5": {"attribute_name": "Abstract", "attribute_value_mlt": [{"subitem_description": "The paper presents a neurorobotics cognitive model explaining the understanding and generalisation of nouns and verbs combinations when a vocal command consisting of a verb-noun sentence is provided to a humanoid robot. The dataset used for training was obtained from object manipulation tasks with a humanoid robot platform; it includes 9 motor actions and 9 objects placing placed in 6 different locations), which enables the robot to learn to handle real-world objects and actions. Based on the multiple time-scale recurrent neural networks, this study demonstrates its generalisation capability using a large data-set, with which the robot was able to generalise semantic representation of novel combinations of noun-verb sentences, and therefore produce the corresponding motor behaviours. This generalisation process is done via the grounding process: different objects are being interacted, and associated, with different motor behaviours, following a learning approach inspired by developmental language acquisition in infants. Further analyses of the learned network dynamics and representations also demonstrate how the generalisation is possible via the exploitation of this functional hierarchical recurrent network.", "subitem_description_type": "Other"}]}, "item_10001_publisher_8": {"attribute_name": "Publisher", "attribute_value_mlt": [{"subitem_publisher": "Springer US"}]}, "item_10001_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:doi/10.1007/s10514-018-9793-7", "subitem_relation_type_select": "DOI"}}]}, "item_10001_relation_16": {"attribute_name": "情報源", "attribute_value_mlt": [{"subitem_relation_name": [{"subitem_relation_name_text": "https://creativecommons.org/licenses/by/4.0/"}]}]}, "item_10001_relation_17": {"attribute_name": "Related site", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://link.springer.com/article/10.1007/s10514-018-9793-7", "subitem_relation_type_select": "URI"}}]}, "item_10001_rights_15": {"attribute_name": "Rights", "attribute_value_mlt": [{"subitem_rights": "© 2018 The Author(s)."}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "0929-5593", "subitem_source_identifier_type": "ISSN"}, {"subitem_source_identifier": "1573-7527", "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_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2019-09-19"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "Zhong-2019-Sensorimotor input as a language ge.pdf", "filesize": [{"value": "2.3 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "Creative Commons Attribution 4.0 International (https://creativecommons.org/licenses/by/4.0/)", "licensetype": "license_free", "mimetype": "application/pdf", "size": 2300000.0, "url": {"label": "Zhong-2019-Sensorimotor input as a language ge", "url": "https://oist.repo.nii.ac.jp/record/1104/files/Zhong-2019-Sensorimotor input as a language ge.pdf"}, "version_id": "6951a12b-0b7a-4fe8-b50f-8c9e1cbb75a9"}]}, "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": "Sensorimotor input as a language generalisation tool: a neurorobotics model for generation and generalisation of noun-verb combinations with sensorimotor inputs", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Sensorimotor input as a language generalisation tool: a neurorobotics model for generation and generalisation of noun-verb combinations with sensorimotor inputs", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "28", "path": ["78"], "permalink_uri": "https://oist.repo.nii.ac.jp/records/1104", "pubdate": {"attribute_name": "公開日", "attribute_value": "2019-09-19"}, "publish_date": "2019-09-19", "publish_status": "0", "recid": "1104", "relation": {}, "relation_version_is_last": true, "title": ["Sensorimotor input as a language generalisation tool: a neurorobotics model for generation and generalisation of noun-verb combinations with sensorimotor inputs"], "weko_shared_id": 28}
Sensorimotor input as a language generalisation tool: a neurorobotics model for generation and generalisation of noun-verb combinations with sensorimotor inputs
https://oist.repo.nii.ac.jp/records/1104
https://oist.repo.nii.ac.jp/records/1104309c0345-f9a3-433c-8254-828c6e21faf8
名前 / ファイル | ライセンス | アクション |
---|---|---|
Zhong-2019-Sensorimotor input as a language ge (2.3 MB)
|
Creative Commons Attribution 4.0 International (https://creativecommons.org/licenses/by/4.0/)
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2019-09-19 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Sensorimotor input as a language generalisation tool: a neurorobotics model for generation and generalisation of noun-verb combinations with sensorimotor inputs | |||||
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) |
Zhong, Junpei
× Zhong, Junpei× Peniak, Martin× Tani, Jun× Ogata, Tetsuya× Cangelosi, Angelo |
|||||
書誌情報 |
en : Autonomous Robots 巻 43, 号 5, p. 1271-1290, 発行日 2018-08-21 |
|||||
抄録 | ||||||
内容記述タイプ | Other | |||||
内容記述 | The paper presents a neurorobotics cognitive model explaining the understanding and generalisation of nouns and verbs combinations when a vocal command consisting of a verb-noun sentence is provided to a humanoid robot. The dataset used for training was obtained from object manipulation tasks with a humanoid robot platform; it includes 9 motor actions and 9 objects placing placed in 6 different locations), which enables the robot to learn to handle real-world objects and actions. Based on the multiple time-scale recurrent neural networks, this study demonstrates its generalisation capability using a large data-set, with which the robot was able to generalise semantic representation of novel combinations of noun-verb sentences, and therefore produce the corresponding motor behaviours. This generalisation process is done via the grounding process: different objects are being interacted, and associated, with different motor behaviours, following a learning approach inspired by developmental language acquisition in infants. Further analyses of the learned network dynamics and representations also demonstrate how the generalisation is possible via the exploitation of this functional hierarchical recurrent network. | |||||
出版者 | ||||||
出版者 | Springer US | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 0929-5593 | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 1573-7527 | |||||
DOI | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | DOI | |||||
関連識別子 | info:doi/10.1007/s10514-018-9793-7 | |||||
権利 | ||||||
権利情報 | © 2018 The Author(s). | |||||
情報源 | ||||||
関連名称 | https://creativecommons.org/licenses/by/4.0/ | |||||
関連サイト | ||||||
識別子タイプ | URI | |||||
関連識別子 | https://link.springer.com/article/10.1007/s10514-018-9793-7 | |||||
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 |