ログイン
言語:

WEKO3

  • トップ
  • ランキング
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

{"_buckets": {"deposit": "3a8b16df-665d-48c0-9983-2bd800369a66"}, "_deposit": {"id": "3051", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "3051"}, "status": "published"}, "_oai": {"id": "oai:niigata-u.repo.nii.ac.jp:00003051", "sets": ["454", "425"]}, "item_5_alternative_title_1": {"attribute_name": "その他のタイトル", "attribute_value_mlt": [{"subitem_alternative_title": "Diversity Maintenance in Genetic Programming"}]}, "item_5_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2006-02", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "3", "bibliographicPageEnd": "230", "bibliographicPageStart": "219", "bibliographicVolumeNumber": "21", "bibliographic_titles": [{"bibliographic_title": "人工知能学会論文誌"}, {"bibliographic_title": "人工知能学会論文誌", "bibliographic_titleLang": "en"}]}]}, "item_5_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "This paper is motivated by an experimental result that better performing genetic programming runs tend to have higher phenotypic diversity. To maintain phenotypic diversity, we apply implicit fitness sharing and its variant, called unfitness multiplying. To apply these methods to problems in which individuals have infinite kinds of possible behaviours, we classify posible behaviours into 50 achievement levels, and assign a reward or a penalty to each level. In implicit fitness sharing a reward is shared out among individuals with the same achievement level, and in unfitness multiplying a penalty is multiplied by the number of individuals with the same level and is distributed to related individuals. Five benchmark problems (11-multiplexer, sextic polynomial, four-sine, intertwined spiral, and artificial ant problems) are used to illustrate the effect of the methods. The results show that our methods clearly promote diversity and lead population to a smooth frequency distribution of achievement levels, and that our methods usually perform better than the original implicit fitness sharing on success rate and the best (raw) fitness. We also observe that the unfitness multiplying makes a quite different ranking over individuals than the one by the implicit fitness sharing.", "subitem_description_type": "Abstract"}]}, "item_5_full_name_3": {"attribute_name": "著者別名", "attribute_value_mlt": [{"nameIdentifiers": [{"nameIdentifier": "40578", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Motoki, Tatsuya"}]}, {"nameIdentifiers": [{"nameIdentifier": "40581", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Numaguchi, Yasushi"}]}]}, "item_5_publisher_7": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "人工知能学会"}]}, "item_5_select_19": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_select_item": "publisher"}]}, "item_5_source_id_11": {"attribute_name": "書誌レコードID", "attribute_value_mlt": [{"subitem_source_identifier": "AA11579226", "subitem_source_identifier_type": "NCID"}]}, "item_5_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "13460714", "subitem_source_identifier_type": "ISSN"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "元木, 達也"}], "nameIdentifiers": [{"nameIdentifier": "40578", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "沼口, 靖"}], "nameIdentifiers": [{"nameIdentifier": "40579", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2019-07-30"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "21_3_219-230.pdf", "filesize": [{"value": "1.6 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 1600000.0, "url": {"label": "21_3_219-230.pdf", "url": "https://niigata-u.repo.nii.ac.jp/record/3051/files/21_3_219-230.pdf"}, "version_id": "bb50b4b3-24b8-4acb-a167-f6f6298d38b4"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "genetic programming", "subitem_subject_scheme": "Other"}, {"subitem_subject": "diversity maintenance", "subitem_subject_scheme": "Other"}, {"subitem_subject": "fitness sharing", "subitem_subject_scheme": "Other"}]}, "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": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "遺伝的プログラミングでの多様性維持について", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "遺伝的プログラミングでの多様性維持について"}, {"subitem_title": "遺伝的プログラミングでの多様性維持について", "subitem_title_language": "en"}]}, "item_type_id": "5", "owner": "1", "path": ["454", "425"], "permalink_uri": "http://hdl.handle.net/10191/21944", "pubdate": {"attribute_name": "公開日", "attribute_value": "2013-04-19"}, "publish_date": "2013-04-19", "publish_status": "0", "recid": "3051", "relation": {}, "relation_version_is_last": true, "title": ["遺伝的プログラミングでの多様性維持について"], "weko_shared_id": null}
  1. 060 工学部
  2. 10 学術雑誌論文
  3. 10 査読済論文
  1. 0 資料タイプ別
  2. 01 学術雑誌論文

遺伝的プログラミングでの多様性維持について

http://hdl.handle.net/10191/21944
http://hdl.handle.net/10191/21944
95c00389-2771-4407-b190-d5d4cc96b264
名前 / ファイル ライセンス アクション
21_3_219-230.pdf 21_3_219-230.pdf (1.6 MB)
Item type 学術雑誌論文 / Journal Article(1)
公開日 2013-04-19
タイトル
タイトル 遺伝的プログラミングでの多様性維持について
タイトル
言語 en
タイトル 遺伝的プログラミングでの多様性維持について
言語
言語 jpn
キーワード
主題Scheme Other
主題 genetic programming
キーワード
主題Scheme Other
主題 diversity maintenance
キーワード
主題Scheme Other
主題 fitness sharing
資源タイプ
資源 http://purl.org/coar/resource_type/c_6501
タイプ journal article
その他のタイトル
その他のタイトル Diversity Maintenance in Genetic Programming
著者 元木, 達也

× 元木, 達也

WEKO 40578

元木, 達也

Search repository
沼口, 靖

× 沼口, 靖

WEKO 40579

沼口, 靖

Search repository
著者別名
識別子 40578
識別子Scheme WEKO
姓名 Motoki, Tatsuya
著者別名
識別子 40581
識別子Scheme WEKO
姓名 Numaguchi, Yasushi
抄録
内容記述タイプ Abstract
内容記述 This paper is motivated by an experimental result that better performing genetic programming runs tend to have higher phenotypic diversity. To maintain phenotypic diversity, we apply implicit fitness sharing and its variant, called unfitness multiplying. To apply these methods to problems in which individuals have infinite kinds of possible behaviours, we classify posible behaviours into 50 achievement levels, and assign a reward or a penalty to each level. In implicit fitness sharing a reward is shared out among individuals with the same achievement level, and in unfitness multiplying a penalty is multiplied by the number of individuals with the same level and is distributed to related individuals. Five benchmark problems (11-multiplexer, sextic polynomial, four-sine, intertwined spiral, and artificial ant problems) are used to illustrate the effect of the methods. The results show that our methods clearly promote diversity and lead population to a smooth frequency distribution of achievement levels, and that our methods usually perform better than the original implicit fitness sharing on success rate and the best (raw) fitness. We also observe that the unfitness multiplying makes a quite different ranking over individuals than the one by the implicit fitness sharing.
書誌情報 人工知能学会論文誌
en : 人工知能学会論文誌

巻 21, 号 3, p. 219-230, 発行日 2006-02
出版者
出版者 人工知能学会
ISSN
収録物識別子タイプ ISSN
収録物識別子 13460714
書誌レコードID
収録物識別子タイプ NCID
収録物識別子 AA11579226
著者版フラグ
値 publisher
戻る
0
views
See details
Views

Versions

Ver.1 2021-03-01 20:18:20.799730
Show All versions

Share

Mendeley Twitter Facebook Print Addthis

Cite as

エクスポート

OAI-PMH
  • OAI-PMH JPCOAR
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by WEKO3


Powered by WEKO3