Tobias Scheffer – författare

This volume contains the papers presented at the 8th International Conference onDiscoveryScience(DS2005)heldinSingapore,RepublicofSingapore,during the days from 8-11 of October 2005. The main objective of the Discovery Science (DS) conference series is to p- vide an open forum for intensive discussions and the exchange of new ideas and information among researchers working in the area of automating scienti?c d- covery or working on tools for supporting the human process of discovery in science. It has been a successful arrangement in the past to co-locate the DS conference with the International Conference on Algorithmic Learning Theory (ALT). This combination of ALT and DS allows for a comprehensive treatment ofthewholerange,fromtheoreticalinvestigationstopracticalapplications.C- tinuing in this tradition, DS 2005 was co-located with the 16th ALT conference (ALT2005).TheproceedingsofALT 2005werepublished asa twinvolume3734 of the LNCS series. TheInternationalSteeringCommitteeoftheDiscoveryScienceconference- ries providedimportantadviceon a number ofissues during the planning of D- coveryScience2005.ThemembersoftheSteeringCommiteeareHiroshiMotoda, (Osaka University), Alberto Apostolico (Purdue University), Setsuo Arikawa (Kyushu University), Achim Ho?mann (University of New South Wales), Klaus P. Jantke (DFKI and FIT Leipzig, Germany), Massimo Melucci (U- versityofPadua),Masahiko Sato(Kyoto University),Ayumi Shinohara(Tohoku University),EinoshinSuzuki(YokohamaNationalUniversity),andThomasZe- mann (Hokkaido University). We received 112 full paper submissions out of which 21 long papers (up to 15 pages), 7 regular papers (up to 9 pages), and 9 project reports (3 pages) were acceptedforpresentationandarepublished inthis volume.Eachsubmissionwas reviewed by at least two members of the Program Committee of international expertsinthe?eld.Theselectionwasmadeaftercarefulevaluationofeachpaper based on originality, technical quality, relevance to the ?eld of discovery science, and clarity.

The two premier annual European conferences in the areas of machine learning anddatamining havebeencollocatedeversincethejointconferenceinFreiburg, Germany,2001. The European Conference on Machine Learning wasestablished 20 years ago, when the ?rst European Working Session on Learning was held in Orsay, France, in 1986. The conference is growing, and is more lively than ever. The European Conference on Principles and Practice of Knowledge Discovery in Databasescelebratesits tenth anniversary;the ?rst PKDD took place in 1997 in Trondheim, Norway. Over the years, the ECML/PKDD series has evolved into one of the largest and most selective international conferences in these areas, the only one that provides a common forum for the two closely related ?elds. In 2006, the 6th collocated ECML/PKDD took place during September 18-22, when the Humboldt-Universität zu Berlin hosted the 17th European Conference on Machine Learning (ECML) and the 10th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD). The successful model of a hierarchical reviewing process that was introduced last year for the ECML/PKDD 2005 in Porto has been taken over in 2006. We nominated 32 Area Chairs, each of them responsible for several closely related research topics. Suitable areas were selected on the basis of the submission s- tistics for ECML/PKDD 2005 to ensure a proper load balance among the Area Chairs. For the ?rst time, a joint Program Committee was nominated for the two conferences, consisting of 280 renowned researchers,mostly proposed by the AreaChairs.

This book constitutes the refereed proceedings of the 17th European Conference on Machine Learning, ECML 2006, held, jointly with PKDD 2006. The book presents 46 revised full papers and 36 revised short papers together with abstracts of 5 invited talks, carefully reviewed and selected from 564 papers submitted. The papers present a wealth of new results in the area and address all current issues in machine learning.

The two premier annual European conferences in the areas of machine learning anddatamining havebeencollocatedeversincethejointconferenceinFreiburg, Germany,2001. The European Conference on Machine Learning wasestablished 20 years ago, when the ?rst European Working Session on Learning was held in Orsay, France, in 1986. The conference is growing, and is more lively than ever. The European Conference on Principles and Practice of Knowledge Discovery in Databasescelebratesits tenth anniversary;the ?rst PKDD took place in 1997 in Trondheim, Norway. Over the years, the ECML/PKDD series has evolved into one of the largest and most selective international conferences in these areas, the only one that provides a common forum for the two closely related ?elds. In 2006, the 6th collocated ECML/PKDD took place during September 18-22, when the Humboldt-Universität zu Berlin hosted the 17th European Conference on Machine Learning (ECML) and the 10th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD). The successful model of a hierarchical reviewing process that was introduced last year for the ECML/PKDD 2005 in Porto has been taken over in 2006. We nominated 32 Area Chairs, each of them responsible for several closely related research topics. Suitable areas were selected on the basis of the submission s- tistics for ECML/PKDD 2005 to ensure a proper load balance among the Area Chairs. For the ?rst time, a joint Program Committee was nominated for the two conferences, consisting of 280 renowned researchers,mostly proposed by the AreaChairs.