Scalable, high-performance data mining with parallel processing

  • Alex Alves Freitas
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1510)


Parallel processing seems to be the great hope to speed up and scale up data mining algorithms, in order to cope with the huge size of real-world databases and data warehouses. However, most projects on parallel data mining have focused on the paralleilization of a single kind of algorithm or knowledge discovery paradigm. This tutorial will present a considerably broader view of the area of parallel data mining. In particular, it will discuss the parallelization of algorithms of four different knowledge discovery paradigms, namely rule induction, instance-based learning (or nearest neighbours), genetic algorithms and neutral networks. In addition, this tutorial will address both the use of “general- purpose” parallel machines and the use of commercially-available parallel database servers. Different parallelization strategies will be discussed and compared, for each of the four above- mentioned knowledge discovery paradigms.

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Alex Alves Freitas
    • 1
  1. 1.CEFET-PR, Dep. de Informatica (DAINF)CuritibaBrazil

Personalised recommendations