Robust boosting algorithm against mislabeling in multiclass problems

Takashi Takenouchi*, Shinto Eguchi, Noboru Murata, Takafumi Kanamori

*この研究の対応する著者

研究成果: Article査読

16 被引用数 (Scopus)

抄録

We discuss robustness against mislabeling in multiclass labels for classification problems and propose two algorithms of boosting, the normalized Eta-Boost.M and Eta-Boost.M, based on the Eta-divergence. Those two boosting algorithms are closely related to models of mislabeling in which the label is erroneously exchanged for others. For the two boosting algorithms, theoretical aspects supporting the robustness for mislabeling are explored.We apply the proposed two boosting methods for synthetic and real data sets to investigate the performance of thesemethods, focusing on robustness, and confirm the validity of the proposed methods.

本文言語English
ページ(範囲)1596-1630
ページ数35
ジャーナルNeural Computation
20
6
DOI
出版ステータスPublished - 2008 6月

ASJC Scopus subject areas

  • 人文科学(その他)
  • 認知神経科学

フィンガープリント

「Robust boosting algorithm against mislabeling in multiclass problems」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル