Welcome!
To use the personalized features of this site, please log in or register.
If you have forgotten your username or password, we can help.
My Menu
Saved Items

An Unsupervised Bayesian Distance Measure

Petri KontkanenContact Information, Jussi LahtinenContact Information, Petri MyllymäkiContact Information and Henry TirriContact Information

(5)  Complex Systems Computation Group (CoSCo) P.O.Box 26, Department of Computer Science, University of Helsinki, FIN-00014, Finland
Abstract
We introduce a distance measure based on the idea that two vectors are considered similar if they lead to similar predictive probability distributions. The suggested approach avoids the scaling problem inherent to many alternative techniques as the method automatically transforms the original attribute space to a probability space where all the numbers lie between 0 and 1. The method is also flexible in the sense that it allows different attribute types (discrete or continuous) in the same consistent framework. To study the validity of the suggested measure, we ran a series of experiments with publicly available data sets. The empirical results demonstrate that the unsupervised distance measure is sensible in the sense that it can be used for discovering the hidden clustering structure of the data.

Contact Information Petri Kontkanen

URL: http://www.cs.Helsinki.FI/research/cosco/

Contact Information Jussi Lahtinen

URL: http://www.cs.Helsinki.FI/research/cosco/

Contact Information Petri Myllymäki

URL: http://www.cs.Helsinki.FI/research/cosco/

Contact Information Henry Tirri

URL: http://www.cs.Helsinki.FI/research/cosco/
Fulltext Preview (Small, Large)
Image of the first page of the fulltext

References secured to subscribers.



Export this chapter
Export this chapter as RIS | Text
 
Referenced by
2 newer articles

  1. Liang, J. (2008) The acquisition and application of similarity knowledge based on consultation in engineering product design. The International Journal of Advanced Manufacturing Technology 37(1-2)
    [CrossRef]
  2. Dubois, D. (2002) Fuzzy set-based methods in instance-based reasoning. IEEE Transactions on Fuzzy Systems 10(3)
    [CrossRef]
Remote Address: 38.107.191.109 • Server: mpweb03
HTTP User Agent: CCBot/1.0 (+http://www.commoncrawl.org/bot.html)