Boosting Learning Algorithm for Pattern Recognition and Beyond

この論文にアクセスする

この論文をさがす

著者

抄録

This paper discusses recent developments for pattern recognition focusing on boosting approach in machine learning. The statistical properties such as Bayes risk consistency for several loss functions are discussed in a probabilistic framework. There are a number of loss functions proposed for different purposes and targets. A unified derivation is given by a generator function <i>U</i> which naturally defines entropy, divergence and loss function. The class of <i>U</i>-loss functions associates with the boosting learning algorithms for the loss minimization, which includes AdaBoost and LogitBoost as a twin generated from Kullback-Leibler divergence, and the (partial) area under the ROC curve. We expand boosting to unsupervised learning, typically density estimation employing <i>U</i>-loss function. Finally, a future perspective in machine learning is discussed.

収録刊行物

  • IEICE transactions on information and systems

    IEICE transactions on information and systems 94(10), 1863-1869, 2011-10-01

    The Institute of Electronics, Information and Communication Engineers

参考文献:  31件中 1-31件 を表示

各種コード

  • NII論文ID(NAID)
    10030193119
  • NII書誌ID(NCID)
    AA10826272
  • 本文言語コード
    ENG
  • 資料種別
    ART
  • ISSN
    09168532
  • データ提供元
    CJP書誌  J-STAGE 
ページトップへ