{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00194829","sets":["1164:4088:9695:9718"]},"path":["9718"],"owner":"44499","recid":"194829","title":["情報理論的尺度に基づく家族的類似クラスターの順序関係の学習可能性について-Bayesian逆強化学習の報酬を家族的類似度と見做すこととは何か-"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-02-28"},"_buckets":{"deposit":"a32ddb05-da27-4d09-b5c8-82daeebddc67"},"_deposit":{"id":"194829","pid":{"type":"depid","value":"194829","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"情報理論的尺度に基づく家族的類似クラスターの順序関係の学習可能性について-Bayesian逆強化学習の報酬を家族的類似度と見做すこととは何か-","author_link":["462233","462234"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"情報理論的尺度に基づく家族的類似クラスターの順序関係の学習可能性について-Bayesian逆強化学習の報酬を家族的類似度と見做すこととは何か-"},{"subitem_title":"On the Possibility of Learning the Order Relation of　Familial Resemblance Clusters based on Information Theoretic Scale—What is meant by \"Defining the Rewards of　Bayesian Inverse Reinforcement Learning as Family Resenblence\"? —","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"国際動向/情報理論","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2019-02-28","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"神奈川大学工学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Kanagawa University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/194829/files/IPSJ-IOT19044020.pdf","label":"IPSJ-IOT19044020.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-IOT19044020.pdf","filesize":[{"value":"589.3 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"43"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"444ec38f-7080-4d5e-aa8c-a1a3362a0db2","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"森住, 哲也"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tetsuya, Morizumi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12326962","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8787","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本論文では， ＜私＞ という視点を人工知能的システムに組み込むアプローチを示す．「それぞれの ＜私＞ が他者性を如何に解釈するか」 という問いに対し，ウイトゲンシュタインの言語ゲームに於ける家族的類似の概念と世阿弥の離見の見の概念を確率モデルによって設計する．確率変数としての存在者は家族的類似として現れる．しかし一方で，その存在者はプレオーダーのテクストの族から全順序のテクストのクラスターヘと再構築されなければならない.そのための必要条件は次に示される ： 「テクストの家族的類似のクラスターの境界となる確率変数の確率分布を学習させる過程｣，即ち 「順序関係の公理にしたがう決定論的なテクストのあつまりを生成する過程」 が確率的に分析される．それにより大量のテクストから家族的類似を満たす順序関係の規則を抽出する．即ち，半順序関係，全順序関係の性質を持つテクストのクラスターが分析されることによって確率的世界から決定の世界の順序関係が導かれる．確率分布の家族的類似は情報理論的尺度の順序関係によって評価される．本論文では，私の意思を示す教師データを使用する，教師ありベイジアン逆強化学習 (Supervised Bayesian Inverse Reinforcement Learning (S-BIRL) ) のグラフイカルモデルを示す．S-BIRL は Blei の supervised LDA の潜在的確率変数を強化学習のアクションの潜在的なパラメーターと解釈し，かつ Ramage の Labeled LDA を強化学習の状態 S のラベルとして解釈するモデルである．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this paper, we present an approach to incorporate the viewpoint of <mind> into an artificial intelligent system. To the question \"How each mind interprets others'\", \"family resemblance\" in Wittgenstein's language game and concepts of \"Riken-no-ken (sight outside of sight)\" used in Ze'ami's treatise on Noh are designed by probabilistic models. Those who exist as stochastic variables appear as family resemblance. But on the other hand, its existence must be reconstructed from the pre-order text group to the total order cluster. The requirements for this are as follows: \"The process of learning the probability distribution of the random variable that becomes the boundary of the familial resemblance clusters of texts\", that is, \"the process of generating a set of deterministic texts that satisfies the axiom of order relation\" is stochastically analyzed . It extracts rules of order relation satisfying the familial resemblance from a large amount of text. That is, by analyzing clusters of texts having partial-order relation and total-order relationship property, the order relation of decision world is derived from stochastic world. Family similarity of probability distribution is evaluated by order relation of information theoretic scale. In this paper, we show a graphical model of Supervised Bayesian Inverse Reinforcement Leaming (S - BIRL) using supervised data. S - BIRL is a model that interprets the potential random variable of Blei 's supervised LDA as a potential parameter of reinforcement learning actions and interprets Ramage's Labeled LDA as a label of reinforcement leaming state S.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告インターネットと運用技術（IOT）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2019-02-28","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"20","bibliographicVolumeNumber":"2019-IOT-44"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T23:19:21.530092+00:00","created":"2025-01-19T00:59:51.497829+00:00","links":{},"id":194829}