Bøger af Jean-Francois Boulicaut

It is our pleasure to present the proceedings of Discovery Science 2008, the 11th International Conference on Discovery Science held in Budapest, Hungary, October 13-16, 2008. It was co-located with ALT 2008, the 19th International Conference on Algorithmic Learning Theory, whose proceedings are available in the twin volume LNAI 5254. This combination of DS and ALT conferences has been successfully organized each year since 2002. It provides a forum for the researchersworking on many di?erent aspects of scienti?c discovery. Indeed, ALT/DS 2008 covered both the possibility to automate part of the scienti?c discoveryandthenecessarysupporttothehumanprocessofdiscoveryinscience. Interestingly, this co-location also provided the opportunity for an exciting joint program of tutorials and invited talks. The number of submitted papers was 58, i.e., slightly more than the previous year. The Program Committee members were involved in a rigorous selection process based on three reviews per paper. At the end, we selected 26 long papers thanks to the recommendations of the experts based on relevance, novelty, signi?cance, technical quality, and clarity. Although some short papers were submitted, none of them was selected.

Introduction The dramatic increase in available computer storage capacity over the last 10 years has led to the creation of very large databases of scienti?c and commercial information. The need to analyze these masses of data has led to the evolution of the new ?eld knowledge discovery in databases (KDD) at the intersection of machine learning, statistics and database technology. Being interdisciplinary by nature, the ?eld o?ers the opportunity to combine the expertise of di?erent ?elds intoacommonobjective.Moreover,withineach?elddiversemethodshave been developed and justi?ed with respect to di?erent quality criteria. We have toinvestigatehowthesemethods cancontributeto solvingthe problemofKDD. Traditionally, KDD was seeking to ?nd global models for the data that - plain most of the instances of the database and describe the general structure of the data. Examples are statistical time series models, cluster models, logic programs with high coverageor classi?cation models like decision trees or linear decision functions. In practice, though, the use of these models often is very l- ited, because global models tend to ?nd only the obvious patterns in the data, 1 which domain experts already are aware of . What is really of interest to the users are the local patterns that deviate from the already-known background knowledge. David Hand, who organized a workshop in 2002, proposed the new ?eld of local patterns.