分割統治による Support Vector Machine の学習の高速化

機関リポジトリ HANDLE Web Site

書誌事項

タイトル別名
  • High-Speed Learning of Support Vector Machine by Divide and Conquer Method
  • ブンカツ トウチ ニ ヨル Support Vector Machine ノ ガクシュウ ノ コウソクカ

この論文をさがす

抄録

Item Response Theory (IRT) is a method to analyze test and test items with assumpitions on the mathematical relationship between abilities and item responses. IRT is used for developing and refining test items in many fields of education. In this work, we carried out an IRT analysis by using data obtained from two types of programming tests. We applied the two parameter logistic model with item parameters aj and bj. The item parameter aj represents the discrimination power of the jth test item, and bj estimates ability, and this is caused partially by the insufficient number of test items.

収録刊行物

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ