Source material for T-122.102, spring 2003

Some articles are linked from this page; all links should be accessible from HUT computers. For articles and books not available on the Web, inquire from the course organizers.

  • Association rules
    • @InProceedings{Agrawal93,
          author = "Rakesh Agrawal and Tomasz Imielinski and Arun N. Swami",
          title = "Mining Association Rules between 
                   Sets of Items in Large Databases",
          booktitle = "Proceedings of the 1993 {ACM} {SIGMOD} 
                       International Conference on Management of Data",
          pages = "207--216"
      }
    • @InProceedings{Mannila94,
          author = "Heikki Mannila and Hannu Toivonen and A. Inkeri Verkamo",
          title = "Efficient algorithms for discovering association rules",
          booktitle = "{AAAI} Workshop on Knowledge Discovery 
                       in Databases ({KDD}-94)",
          publisher = "AAAI Press",
          address = "Seattle, Washington",
          editor = "Usama M. Fayyad and Ramasamy Uthurusamy",
          pages = "181--192",
          year = "1994"
      }
    • @Article{Mannila97,
          author = "Heikki Mannila and Hannu Toivonen and A. Inkeri Verkamo",
          title = "Discovery of Frequent Episodes in Event Sequences",
          journal = "Data Mining and Knowledge Discovery",
          volume = "1",
          number = "3",
          pages = "259--289",
          year = "1997"
      }
    • @TechReport{Pavlov01,
        author =	 {Dmitry Pavlov and Heikki Mannila and Padhraic Smyth},
        title =	 {Beyond Independence: Probabilistic Models for Query
                        Approximation on Binary Transaction Data},
        institution =	 {UC Irvine},
        year =	 2001,
        number =	 {UCI-ICS TR-01-09}
      }
    • @Article{Castelo2001,
          author = "Robert Castelo and Ad Feelders and Arno Siebes",
          title = "{MAMBO}: Discovering Association Rules Based on Conditional Independencies",
          journal = "Lecture Notes in Computer Science",
          volume = "2189",
          pages = "289--298",
          year = "2001",
          url = "citeseer.nj.nec.com/463070.html" 
      }

      (also at Springer LINK)

  • HITS & PageRank
    • @Article{Kleinberg99,
          author = "Jon M. Kleinberg",
          title = "Authoritative sources in a hyperlinked environment",
          journal = "Journal of the ACM",
          volume = "46",
          number = "5",
          pages = "604--632",
          year = "1999"
      }
    • @InProceedings{Ng2001,
        author =	 {Andrew Y. Ng and Alice X. Zheng and Michael I.
                        Jordan},
        title =	 {Stable Algorithms for Link Analysis},
        booktitle =	 {Proc. 24th Annual Intl. ACM SIGIR Conference},
        year =	 2001,
        organization = {ACM}
      }
    • @TechReport{Ding2002,
        author =	 {Chris Ding and Xiaofeng He and Parry Husbands and
                        Hongyuan Zha and Horst Simon},
        title =	 {{PageRank}, {HITS} and a Unified Framework for Link
                        Analysis},
        institution =	 {LBNL},
        year =	 2002,
        number =	 49372
      }
      
  • Probabilistic clustering
    • @Article{Wolfe1970,
        author = 	 {John W. Wolfe},
        title = 	 {Pattern Clustering by Multivariate Mixture Analysis},
        journal = 	 {Multivariate Behavioral Research},
        year = 	 {1970},
        volume = 	 {5},
        pages = 	 {329--350},
        month = 	 {July},
      }
    • @Book{Everitt81,
        author = 	 {B.S. Everitt and D.J. Hand},
        title = 	 {Finite Mixture Distributions},
        publisher = 	 {Chapman and Hall},
        year = 	 {1981},
        series = 	 {Monographs on Applied Probability and Statistics},
      }
  • Non-identifiability of finite mixtures of Bernoulli distributions
    • @Article{Gyllenberg1994,
        author = 	 {Mats Gyllenberg and Timo Koski and Edwin Reilink and
                        Martin Verlaan},
        title = 	 {Non-uniqueness in probabilistic numerical identification
                        of bacteria},
        journal = 	 {Journal of Applied Probability},
        year = 	 {1994},
        volume = 	 {31},
        number = 	 {2},
        pages = 	 {542--548},
        month = 	 {June}
      }
    • @Article{Carreira2000,
        author = 	 {Miguel A. Carreira-Perpinan and Steve Renals},
        title = 	 {Practical identifiability of finite mixtures of
                        multivariate Bernoulli distributions},
        journal = 	 {Neural Computation},
        year = 	 {2000},
        volume = 	 {12},
        number = 	 {1},
        pages = 	 {141--152},
        month = 	 {January}
      }
  • Generalized linear models
    • @Article{Nelder72,
        author = 	 {J.A. Nelder and R.W.M. Wedderburn},
        title = 	 {Generalized Linear Models},
        journal = 	 {Journal of the Royal Statistical Society, Series A},
        year = 	 {1972},
        volume = 	 {135},
        number = 	 {3},
        pages = 	 {370--384},
      }
    • @Article{Myers97,
        author = 	 {Raymond H. Myers and Douglas C. Montgomery},
        title = 	 {A Tutorial on Generalized Linear Models},
        journal = 	 {Journal of Quality Technology},
        year = 	 {1997},
        volume = 	 {29},
        number = 	 {3},
        pages = 	 {273--291},
        month = 	 {July},
        annote = 	 {ISSN 0022-4065}
      }
  • Bayesian analysis of Generalized linear models
    • @Article{Oh97,
        author = 	 {Man-Suk Oh},
        title = 	 {A Gibbs Sampling Approach to Bayesian Analysis of
                        Generalized Linear Models for Binary data},
        journal = 	 {Computational Statistics},
        year = 	 {1997},
        volume = 	 {12},
        number = 	 {4},
        pages = 	 {431--445},
        annote = 	 {ISSN 0723-712X}
      }


http://www.cis.hut.fi/Opinnot/T-122.102/k2003/material.shtml
t122102@mail.cis.hut.fi
Tuesday, 01-Apr-2003 10:20:29 EEST