{"created":"2023-05-15T14:21:32.018974+00:00","id":3219,"links":{},"metadata":{"_buckets":{"deposit":"8f54b7ab-44a1-4c22-8c9e-623718feb846"},"_deposit":{"created_by":3,"id":"3219","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"3219"},"status":"published"},"_oai":{"id":"oai:bunkyo.repo.nii.ac.jp:00003219","sets":["1:26:226"]},"author_link":["4168"],"item_5_biblio_info_13":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"1999-01-01"},"bibliographicPageEnd":"210","bibliographicPageStart":"151","bibliographicVolumeNumber":"22","bibliographic_titles":[{"bibliographic_title":"情報研究"},{"bibliographic_title":"Information and Communication Studies"}]}]},"item_5_date_43":{"attribute_name":"作成日","attribute_value_mlt":[{"subitem_date_issued_datetime":"2011-02-22"}]},"item_5_description_12":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"　認識システムは、パターン生成システムがその表現をパターンに託したカテゴリがどのカテゴリであるかは知らないという仮定(認識システムの、パターン生成に関する無知仮定)の下で、通信系に関するシャノンの確率模型、言語行為の\"水谷の確率模型\"に対応して、認識行為の確率模型が提案されている。\n　パターン生成、パターン認識の場面において、無曖昧性が実現されるとは、効用としての平均正解率が最大になっている場合の特別な状況である事実を、2定理3.1,3.2の系1で明らかにすることが本研究の目的である。\n　パターン表現(パターン生成)システムの、各カテゴリのパターンによる表現能力が劣っていれば、効用として採用された平均正解率を維持するためには、パターンがどのカテゴリを表すために生成されたかを推定する機能を備えているパターン認識システムの、パターン認識能力が優秀でなければならないし、また、表現能力が優秀であれば、認識能力が劣っていてもよいことを説明可能な\"パターン生成・パターン認識に関する最大化原理理\"が研究されている。\n　パターン認識の働きの底には、パターン生成のもたらす\"典型的なパターンからの崩れ・変形\"に応じ、平均正解率を最大ならしめようとする\"最大化原理\"が流れていることが明らかになっている。\n　本研究により、パターン生成の働きの正確さに応じ、パターン認識の働きが考えられることが鮮明になった。\n\\n　Let us suppose a recognition system does not know to whose category a pattern in question which is generated by a pattern representation belongs. This assumotion is needed to construct a probabilistic model of an action of a generation and a recognition presented here. The model corresponds to the probabilistic model of an action of a representation and an interpretation by use of a language suggested by Sizuo Mizutani.\n　Two corollaries of theorem 3.1 and 3.2 pointed out the greatest correct recognition-rate of the greatest pattern-set. That is to say, a realization of the nonambiguity in pattern generation and pattern recognition means a special case of that an average rate of correct solution is maximized.\n　An analysis presented here clarified that both the pattern generation (or representation) system and the pattern recognition system must obtain a maximum of an average rate of correct solution and that the one must compensate an incomplete faculty of the other.","subitem_description_type":"Abstract"}]},"item_5_description_38":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_description":"application/pdf","subitem_description_type":"Other"}]},"item_5_source_id_19":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"03893367"}]},"item_5_text_39":{"attribute_name":"本文言語","attribute_value_mlt":[{"subitem_text_value":"日本語"}]},"item_5_text_42":{"attribute_name":"ID","attribute_value_mlt":[{"subitem_text_value":"BKSJ220007"}]},"item_5_text_7":{"attribute_name":"Author","attribute_value_mlt":[{"subitem_text_value":"Suzuki, Shoichi"}]},"item_5_text_8":{"attribute_name":"所属機関","attribute_value_mlt":[{"subitem_text_value":"文教大学情報学部"}]},"item_5_text_9":{"attribute_name":"Institution","attribute_value_mlt":[{"subitem_text_value":"Bunkyo University Faculty of Information and Communications"}]},"item_5_version_type_35":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_type":"VoR"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"鈴木, 昇一"}],"nameIdentifiers":[{}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2018-03-24"}],"displaytype":"detail","filename":"BKSJ220007.pdf","filesize":[{"value":"3.2 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"BKSJ220007.pdf","url":"https://bunkyo.repo.nii.ac.jp/record/3219/files/BKSJ220007.pdf"},"version_id":"56ed261a-b950-42af-8efb-821bb94b7217"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"パターン生成"},{"subitem_subject":"シヤノンの通信モデル"},{"subitem_subject":"平均正解率"},{"subitem_subject":"生成行列"},{"subitem_subject":"認識行列"},{"subitem_subject":"認識行為の確率モデル"},{"subitem_subject":"認識行為の無曖昧性"},{"subitem_subject":"健全性"},{"subitem_subject":"完全性"}]},"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":"departmental bulletin paper","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"認識行為に向けての、効用最大化原理","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"認識行為に向けての、効用最大化原理"},{"subitem_title":"A Maximum Principle of Utility for the Action of Recognition"}]},"item_type_id":"5","owner":"3","path":["226"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-02-22"},"publish_date":"2011-02-22","publish_status":"0","recid":"3219","relation_version_is_last":true,"title":["認識行為に向けての、効用最大化原理"],"weko_creator_id":"3","weko_shared_id":-1},"updated":"2023-05-16T16:46:20.867555+00:00"}