WEKO3
アイテム
{"_buckets": {"deposit": "22729b56-18d5-447e-ba3c-49213384ebb5"}, "_deposit": {"created_by": 33, "id": "2673", "owners": [33], "pid": {"revision_id": 0, "type": "depid", "value": "2673"}, "status": "published"}, "_oai": {"id": "oai:oist.repo.nii.ac.jp:00002673", "sets": ["26"]}, "author_link": ["17289", "17284", "17283", "17286", "17285", "17287", "17288", "17290"], "item_10001_biblio_info_7": {"attribute_name": "Bibliographic Information", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2022-03-23", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "312", "bibliographicPageStart": "293", "bibliographicVolumeNumber": "150", "bibliographic_titles": [{}, {"bibliographic_title": "Neural Networks", "bibliographic_titleLang": "en"}]}]}, "item_10001_creator_3": {"attribute_name": "Author", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Taniguchi, Tadahiro"}], "nameIdentifiers": [{"nameIdentifier": "17283", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Yamakawa, Hiroshi"}], "nameIdentifiers": [{"nameIdentifier": "17284", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Nagai, Takayuki"}], "nameIdentifiers": [{"nameIdentifier": "17285", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Doya, Kenji"}], "nameIdentifiers": [{"nameIdentifier": "17286", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Sakagami, Masamichi"}], "nameIdentifiers": [{"nameIdentifier": "17287", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Suzuki, Masahiro"}], "nameIdentifiers": [{"nameIdentifier": "17288", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Nakamura, Tomoaki"}], "nameIdentifiers": [{"nameIdentifier": "17289", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Taniguchi, Akira"}], "nameIdentifiers": [{"nameIdentifier": "17290", "nameIdentifierScheme": "WEKO"}]}]}, "item_10001_description_5": {"attribute_name": "Abstract", "attribute_value_mlt": [{"subitem_description": "Building a human-like integrative artificial cognitive system, that is, an artificial general intelligence (AGI), is the holy grail of the artificial intelligence (AI) field. Furthermore, a computational model that enables an artificial system to achieve cognitive development will be an excellent reference for brain and cognitive science. This paper describes an approach to develop a cognitive architecture by integrating elemental cognitive modules to enable the training of the modules as a whole. This approach is based on two ideas: (1) brain-inspired AI, learning human brain architecture to build human-level intelligence, and (2) a probabilistic generative model (PGM)-based cognitive architecture to develop a cognitive system for developmental robots by integrating PGMs. The proposed development framework is called a whole brain PGM (WB-PGM), which differs fundamentally from existing cognitive architectures in that it can learn continuously through a system based on sensory-motor information.\n\nIn this paper, we describe the rationale for WB-PGM, the current status of PGM-based elemental cognitive modules, their relationship with the human brain, the approach to the integration of the cognitive modules, and future challenges. Our findings can serve as a reference for brain studies. As PGMs describe explicit informational relationships between variables, WB-PGM provides interpretable guidance from computational sciences to brain science. By providing such information, researchers in neuroscience can provide feedback to researchers in AI and robotics on what the current models lack with reference to the brain. Further, it can facilitate collaboration among researchers in neuro-cognitive sciences as well as AI and robotics.", "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": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:pmid/35339010", "subitem_relation_type_select": "PMID"}}]}, "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/10.1016/j.neunet.2022.02.026", "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/S0893608022000673?via%3Dihub", "subitem_relation_type_select": "URI"}}]}, "item_10001_rights_15": {"attribute_name": "Rights", "attribute_value_mlt": [{"subitem_rights": "© 2022 The Authors."}]}, "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_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": "2022-07-04"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "1-s2.0-S0893608022000673-main.pdf", "filesize": [{"value": "1.6 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "Creative Commons Attribution 4.0 International (https://creativecommons.org/licenses/by/4.0/)\n", "licensetype": "license_free", "mimetype": "application/pdf", "size": 1600000.0, "url": {"label": "1-s2.0-S0893608022000673-main", "url": "https://oist.repo.nii.ac.jp/record/2673/files/1-s2.0-S0893608022000673-main.pdf"}, "version_id": "9eb32e82-3f81-465f-8d3b-ad3a374a5c63"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Cognitive architecture", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Probabilistic generative model", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Brain-inspired artificial intelligence", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Artificial general intelligence", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Developmental robotics", "subitem_subject_language": "en", "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": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "33", "path": ["26"], "permalink_uri": "https://oist.repo.nii.ac.jp/records/2673", "pubdate": {"attribute_name": "公開日", "attribute_value": "2022-07-04"}, "publish_date": "2022-07-04", "publish_status": "0", "recid": "2673", "relation": {}, "relation_version_is_last": true, "title": ["A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots"], "weko_shared_id": 33}
A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots
https://oist.repo.nii.ac.jp/records/2673
https://oist.repo.nii.ac.jp/records/267393192df3-3242-4456-8b8c-cb0f7be16a9c
名前 / ファイル | ライセンス | アクション |
---|---|---|
1-s2.0-S0893608022000673-main (1.6 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 | 2022-07-04 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | Cognitive architecture | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | Probabilistic generative model | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | Brain-inspired artificial intelligence | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | Artificial general intelligence | |||||
キーワード | ||||||
言語 | en | |||||
主題Scheme | Other | |||||
主題 | Developmental robotics | |||||
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) |
Taniguchi, Tadahiro
× Taniguchi, Tadahiro× Yamakawa, Hiroshi× Nagai, Takayuki× Doya, Kenji× Sakagami, Masamichi× Suzuki, Masahiro× Nakamura, Tomoaki× Taniguchi, Akira |
|||||
書誌情報 |
en : Neural Networks 巻 150, p. 293-312, 発行日 2022-03-23 |
|||||
抄録 | ||||||
内容記述タイプ | Other | |||||
内容記述 | Building a human-like integrative artificial cognitive system, that is, an artificial general intelligence (AGI), is the holy grail of the artificial intelligence (AI) field. Furthermore, a computational model that enables an artificial system to achieve cognitive development will be an excellent reference for brain and cognitive science. This paper describes an approach to develop a cognitive architecture by integrating elemental cognitive modules to enable the training of the modules as a whole. This approach is based on two ideas: (1) brain-inspired AI, learning human brain architecture to build human-level intelligence, and (2) a probabilistic generative model (PGM)-based cognitive architecture to develop a cognitive system for developmental robots by integrating PGMs. The proposed development framework is called a whole brain PGM (WB-PGM), which differs fundamentally from existing cognitive architectures in that it can learn continuously through a system based on sensory-motor information. In this paper, we describe the rationale for WB-PGM, the current status of PGM-based elemental cognitive modules, their relationship with the human brain, the approach to the integration of the cognitive modules, and future challenges. Our findings can serve as a reference for brain studies. As PGMs describe explicit informational relationships between variables, WB-PGM provides interpretable guidance from computational sciences to brain science. By providing such information, researchers in neuroscience can provide feedback to researchers in AI and robotics on what the current models lack with reference to the brain. Further, it can facilitate collaboration among researchers in neuro-cognitive sciences as well as AI and robotics. |
|||||
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 | isIdenticalTo | |||||
識別子タイプ | PMID | |||||
関連識別子 | info:pmid/35339010 | |||||
DOI | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | DOI | |||||
関連識別子 | info:doi/10.1016/j.neunet.2022.02.026 | |||||
権利 | ||||||
権利情報 | © 2022 The Authors. | |||||
関連サイト | ||||||
識別子タイプ | URI | |||||
関連識別子 | https://www.sciencedirect.com/science/article/pii/S0893608022000673?via%3Dihub | |||||
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 |