See this document in CiteSeerX!

An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering (1997)  (Make Corrections)  (34 citations)
Michael Kearns, Yishay Mansour, Andrew Y. Ng



  Home/Search   Context   Related

Links:   ACM   DBLP

 
View or download:
cmu.edu/scs/ri/glearn/...uai97clust.ps
math.tau.ac.il/~mansour/...97uai.ps.gz
berkeley.edu/~ang/pape...uai97clust.ps
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  cmu.edu/~an2i/ (more)
From:  math.tau.ac.il/~mansour/cv
(Enter author homepages)

Rate this article: (best)
  Comment on this article  
(Enter summary)

Abstract: Assignment methods are at the heart of many algorithms for unsupervised learning and clustering --- in particular, the well-known K-means and Expectation-Maximization (EM) algorithms. In this work, we study several different methods of assignment, including the "hard" assignments used by K-means and the "soft" assignments used by EM. While it is known that K-means minimizes the distortion on the data and EM maximizes the likelihood, little is known about the systematic differences of behavior ... (Update)

Cited by:   More
Algorithms for Clustering High Dimensional and - Tao   (Correct)
An Algorithm for Non-distance Based Clustering in High.. - Zhu, Li (2002)   (Correct)
An MDL Framework for Data Clustering - Kontkanen, Myllymäki, Buntine.. (2003)   (Correct)

Active bibliography (related documents):   More   All
0.0:   Investigation of the Use of Neural Networks for Computerised.. - Shane Dickson (1998)   (Correct)
0.0:   Stereoscopic And Velocimetric Reconstructions Of.. - D. Douxchamps, D. .. (2005)   (Correct)
0.0:   Local Learning in Probabilistic Networks With Hidden Variables - Russell (1995)   (Correct)

Similar documents based on text:   More   All
0.3:   An Experimental and Theoretical Comparison of Model.. - Kearns, Mansour, Ng, Ron   (Correct)
0.2:   AntClass: discovery of clusters in numeric data by an.. - Monmarché, Slimane.. (1999)   (Correct)
0.1:   Early Experience with a Hybrid Processor: K-Means.. - Gokhale, Frigo.. (2000)   (Correct)

Related documents from co-citation:   More   All
14:   Maximum Likelihood from Incomplete Data via the EM Algorithm (context) - Dempster, Laird et al. - 1977
11:   Algorithms for Clustering Data (context) - Jain, Dubes - 1988
8:   Impact of similarity measures on web-page clustering - Strehl, Ghosh et al. - 2000

BibTeX entry:   (Update)

Kearns, M., Mansour, Y., and Ng, A. Y. (1997). An information-theoretic analysis of hard and soft assignment methods for clustering. In Proceedings of Uncertainty in Artificial Intelligence. AAAI. http://citeseer.ist.psu.edu/kearns97informationtheoretic.html   More

@inproceedings{ kearnsinformationtheoretic,
    author = "Michael Kearns and Yishay Mansour and Andrew Y. Ng",
    title = "An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering",
    pages = "282--293",
    url = "citeseer.ist.psu.edu/kearns97informationtheoretic.html" }
Citations (may not include all citations):
2528   Maximum-likelihood from incomplete data via the em algorithm (context) - Dempster, Laird et al. - 1977
2319   Elements of Information Theory (context) - Cover, Thomas - 1991  ACM
2133   Pattern Classification and Scene Analysis (context) - Duda, Hart - 1973
1056   Introduction to the Theory of Neural Computation (context) - Hertz, Krogh et al. - 1991  ACM
653   Fundamentals of Speech Recognition (context) - Rabiner, Juang - 1993  ACM
283   Some methods for classification and analysis of multivariate.. - MacQueen - 1967
107   The EM algorithm for graphical association models with missi.. (context) - Lauritzen - 1995  ACM
93   IEEE Transactions on Information Theory (context) - Gersho, structure et al. - 1982



The graph only includes citing articles where the year of publication is known.


Documents on the same site (http://www.cs.cmu.edu/~an2i/):   More
Applying Online Search Techniques to Reinforcement Learning - Scott Davies (1998)   (Correct)
An Experimental and Theoretical Comparison of Model.. - Kearns, Mansour, Ng, Ron (1995)   (Correct)
Preventing "Overfitting" of Cross-Validation Data - Ng (1997)   (Correct)

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC