Learning with membership queries to minimize prediction error

Yoshifumi Ukita, Toshiyasu Matsushima, Shigeichi Hirasawa

研究成果: Conference article査読

抄録

In this paper, we consider the problem to predict the class of an unknown sample after learning from queries. We propose to evaluate a learning algorithm by a loss function for the prediction under a constraint. In this paper, the error probability for the prediction and the number of queries is defined as the loss function and the constraint, respectively. Then our objective is to minimize the error probability, the error probability is determined by what presentation order for instances to query and how to predict. Since the optimal prediction has been shown in previous researches, we only have to select the optimal presentation order for instances to query. We propose a lower bound used in the branch-and-bound algorithm to select the optimal presentation order for instances. Lastly, we show the efficiency of the algorithm using the derived lower bound by numerical computation.

本文言語English
ページ(範囲)4412-4417
ページ数6
ジャーナルProceedings of the IEEE International Conference on Systems, Man and Cybernetics
5
出版ステータスPublished - 1997 12 1
イベントProceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5) - Orlando, FL, USA
継続期間: 1997 10 121997 10 15

ASJC Scopus subject areas

  • 制御およびシステム工学
  • ハードウェアとアーキテクチャ

フィンガープリント

「Learning with membership queries to minimize prediction error」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