Detail of Publication

Text Language	English
Authors	Masakazu Iwamura, Shinichiro Omachi, and Hirotomo Aso
Title	On the Bias of Predictive Distribution in Pattern Recognition
Journal	Systems and Computers in Japan
Vol.	36
No.	5
Pages	pp.45-54
Publisher	John Wiley & Sons, Inc.
Reviewed or not	Not reviewed
Month & Year	May 2005
Abstract	To estimate distribution from training samples, the maximum likelihood estimation treats the unknown parameter of the distribution as a constant. On the other hand, Bayesian estimation treats the parameter as a random variable. In pattern recognition, Bayesian estimation has been known to improve recognition accuracy. However, it was pointed out that the Bayesian estimation is not effective due to the bias of the likelihood when sample sizes of classes are not the same. In this paper, we show recognition accuracy is improved by modifying the bias of the likelihood when sample sizes are not the same. This indicates that the cause of the ineffectiveness is the bias. We derive the formula of the bias of Geisser's predictive distribution without any approximation, and show a way of modification of the bias of the likelihood. We confirm effectiveness of the proposed method in experiments. In addition, the derived formula gives the theoretical background of a known empirical knowledge.

• Note
  PDF file is available at http://www3.interscience.wiley.com/cgi-bin/jissue/110429145.
• Entry for BibTeX

  @Article{Iwamura2005,
    author =	{Masakazu Iwamura and Shinichiro Omachi and Hirotomo Aso},
    title =	{On the Bias of Predictive Distribution in Pattern Recognition},
    journal =	{Systems and Computers in Japan},
    year =	2005,
    month =	may,
    volume =	{36},
    number =	{5},
    pages =	{45--54},
    publisher =	{John Wiley \& Sons, Inc.}
  }
  
  
  

Back to list