MACHINE LEARNING AND APPLICATIONS
Advanced Course on Artificial Intelligence 1999 (ACAI’99)
5-16 July 1999, Chania, Greece
(http://www.iit.demokritos.gr/skel/eetn/acai99)
European Coordinating Committee on Artificial Intelligence (ECCAI)
(http://www.eccai.org)
&
Hellenic Artificial Intelligence Society (EETN)
(http://www.iit.demokritos.gr/skel/eetn)
This workshop addresses an important aspect related to the Data Mining (DM) and Machine Learning (ML) in pre-processing and analyzing real-world data.
First, the data which are to be processed by a DM algorithm are usually noisy and often inconsistent. Many steps are involved before the actual data analysis starts. Moreover, the genuine logical ML systems do not easily allow processing of numerical attributes as well as numerical (continuous) classes. Therefore, certain procedures have to precede the actual data analysis process.
Second, a result of a genuine ML algorithm, such as a decision tree or a set of decision rules, need not be perfect from the view of custom or commercial applications. It is quite known that a concept description as a result of an inductive process has to be usually processed by a pre- or post-pruning procedure. Other post-processing procedures include rule quality processing, rule filtering, rule combination, or even knowledge integration. All these procedures provide a kind of "symbolic filter" for noisy, imprecise, or "non-user-friendly" knowledge derived by an inductive algorithm.
Thus, the pre- and post-processing tools always help the DM algorithms to investigate databases as well as to refine the acquired knowledge. Usually, these tools exploit techniques that are not genuinely logical, e.g., statistics, neural nets, and others.
These reasons let us to launch this workshop. In fact, we would like to support both theoretical aspects of this issue and practical, experienced, empirical applications. As for the latter, we would like to focus on industry and business applications, but we will review any functional application of the above concern in any discipline.
The theme of this workshop is directly related to the "Machine Learning and Applications" conference:
A. (Fazel) Famili (chair)
Editor-in-Chief, Intelligent Data Analysis http://www.elsevier.com/locate/ida
Phone: +1-613-9938554
Institute for Information Technology Fax : +1-613-9527151
National Research Council of Canada, Email: Fazel.Famili@iit.nrc.ca
Bldg. M-50, Montreal Rd. Ottawa, Ont. http://iit.nrc.ca/~fazel
Canada K1A 0R6
Ivan Bruha (contact person)
http://www.cas.mcmaster.ca/~bruha
McMaster University Phone: +1-905-5259140 ext 23439
Dept. Computing & Software Fax: +1-905-5240340
Hamilton, Ont. Email: bruha@mcmaster.ca
Canada L8S 4L7
Jan Zizka http://www.fi.muni.cz/~zizka
Phone: ++420-5-41512 337
Masaryk University, Faculty of Infomatics Fax: ++420-5-41212568
Dept. of Information Technologies Email: zizka@informatics.muni.cz
Botanicka 68a, 602 00 Brno
Czech Republic
There will be one or two invited talks on the workshop which will survey the given topic as well as introduce their own research.
Up to 10 accepted papers will be presented (each 15-20 min). If there is a larger interest, then some papers might be accepted as posters.
The workshop will take place during the afternoon sessions of ACAI-99, from 14:30 to 18:00. Depending on the number of accepted papers the workshop will take place one or two afternoon sessions. The exact date of the workshop will be finalized by the ACAI-99 organizing committee by the end of Dec-98.
Anyone registered for the main ACAI-99 event can also attend all the workshops. For the workshop participants who will not be registered for the whole ACAI-99 there will be a fee that will be finalized soon.
Proceedings will be published as a technical report in collaboration with the ACAI-99 organization committee.
Please note that authors of the best papers will be invited to submit an extended version of their papers to the Intelligent Data Analysis Journal (http://www.elsevier.com/locate/ida), or even a special issue of the journal regarding this topic might be published.