WEKO3
アイテム
A Proposal of Machine Learning by Rule Generation from Tables with Non-deterministic Information and Its Prototype System
http://hdl.handle.net/10228/00006835
http://hdl.handle.net/10228/00006835b9e1f2e2-d9a3-44e9-8cc9-16564b4fa506
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
ijcrs_535_551.pdf (1.3 MB)
|
|
| アイテムタイプ | 会議発表論文 = Conference Paper(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2018-06-22 | |||||
| 資源タイプ | ||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||
| 資源タイプ | conference paper | |||||
| タイトル | ||||||
| タイトル | A Proposal of Machine Learning by Rule Generation from Tables with Non-deterministic Information and Its Prototype System | |||||
| 言語 | en | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 著者 |
酒井, 浩
× 酒井, 浩× Nakata, Michinori× Watada, Junzo |
|||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | A logical framework on Machine Learning by Rule Generation (MLRG) from tables with non-deterministic information is proposed, and its prototype system in SQL is implemented. In MLRG, the certain rules defined in Rough Non-deterministic Information Analysis (RNIA) are obtained at first, and each uncertain attribute value is estimated so as to cause the certain rules as many as possible, because the certain rules show us the most reliable information. This strategy is similar to the maximum likelihood estimation in statistics. By repeating this process, a standard table and the rules in its table are learned (or estimated) from a given table with non-deterministic information. Even though it will be hard to know the actual unknown values, MLRG will give a plausible estimation value. | |||||
| 備考 | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | International Joint Conference on Rough Sets (IJCRS 2017), 3-7 July, 2017, Olsztyn, Poland | |||||
| 書誌情報 |
Lecture Notes in Computer Science 巻 10313, p. 535-551, 発行日 2017-06-22 |
|||||
| 出版社 | ||||||
| 出版社 | Springer, Cham | |||||
| DOI | ||||||
| 関連タイプ | isVersionOf | |||||
| 識別子タイプ | DOI | |||||
| 関連識別子 | info:doi/10.1007/978-3-319-60837-2_43 | |||||
| ISBN | ||||||
| 識別子タイプ | ISBN | |||||
| 関連識別子 | 978-3-319-60836-5 | |||||
| ISBN | ||||||
| 識別子タイプ | ISBN | |||||
| 関連識別子 | 978-3-319-60837-2 | |||||
| 著作権関連情報 | ||||||
| 権利情報 | Copyright (c) Springer International Publishing AG 2017 | |||||
| 著作権関連情報 | ||||||
| 権利情報 | The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-60837-2_43 | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | Machine learning by rule generation | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | Uncertainty | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | NIS-Apriori algorithm | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | SQL | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | Prototype | |||||
| 出版タイプ | ||||||
| 出版タイプ | AM | |||||
| 出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa | |||||
| 査読の有無 | ||||||
| 値 | yes | |||||
| 研究者情報 | ||||||
| URL | https://hyokadb02.jimu.kyutech.ac.jp/html/133_ja.html | |||||
| 論文ID（連携） | ||||||
| 値 | 10305669 | |||||
| 連携ID | ||||||
| 値 | 6205 | |||||
