Fuer alle an Theorie und Praxis des Maschinellen Lernens
Interessierten:
EINLADUNG ZUR TEILNAHME UND VORLAEUFIGES PROGRAMM:
----------------------------------------------------------------------------
9th EUROPEAN CONFERENCE ON MACHINE LEARNING (ECML-97)
23.-26.April 1997, Prag
----------------------------------------------------------------------------
Vom 23.-26. April 1997 findet in Prag die
9th European Conference on Machine Learning (ECML-97) statt.
Es handelt sich dabei um *die* wissenschaftliche Veranstaltung
zum Themenkreis Maschinelles Lernen in Europa. Alle, die sich
fuer die neuesten Entwicklungen im Bereich des Maschinellen Lernens
interessieren, sind herzlich zur Teilnahme eingeladen.
Wissenschaftliches Programm:
Das wissenschaftliche Programm der ECML-97 von Mittwoch, 23. bis
Freitag, 25.April besteht aus drei eingeladenen Vortragen
sowie aus 25 Plenarvortraegen, die aus 74 eingereichten Arbeiten
ausgewaehlt wurden und einen Einblick in die derzeitige europaeische
Forschung bieten (und nicht nur die europaeische -- es sind u.a.
auch Arbeiten aus den USA, Kanada, Singapur und Neuseeland vertreten).
Eingeladene Vortragende:
STUART RUSSELL (University of California, Berkeley, USA),
Traeger des IJCAI-95 Computers and Thought Award,
wird seine aktuellsten Forschungsergebnisse auf dem Gebiet
des Lernens und Schlussfolgerns unter Unsicherheit praesentieren
("Uncertain Learning Agents");
LUC STEELS (Freie Universitaet Bruessel und Sony Computer
Science Laboratory, Paris) berichtet ueber den derzeitigen Stand
seines Modells des interaktiven und sozialen Lernens in Gruppen
von virtuellen Agenten ("Constructing and Sharing Perceptual
Distinctions"), und
PAUL VITANYI (Universitaet Amsterdam) beleuchtet
grundlegende Fragen des Lernens aus der Sicht der
Komplexitaetstheorie ("On Prediction by Data Compression").
ECML-97/MLNet Workshops:
Im Anschluss an die Konferenz (26.April) finden 4 spezialisierte
Workshops statt (siehe unten), die vom European Network of
Excellence in Machine Learning (MLNet) organisiert werden.
Diese stehen nicht nur Mitgliedern des MLNet offen.
Proceedings:
Die Konferenzproceedings werden in der "Lecture Notes in AI"-Serie
des Springer Verlags erscheinen:
Maarten van Someren & Gerhard Widmer (Eds.) (1997).
Machine Learning: ECML-97.
Lecture Notes in Artificial Intelligence # 1224.
Berlin - Heidelberg: Springer Verlag.
Naehere Informationen:
Univ.-Doz. Dr. Gerhard WIDMER
Programme Co-Chair, ECML-97
Oesterreichisches Forschungsinstitut fuer Artificial Intelligence
Schottengasse 3, 1010 Wien
Tel. 535 32 81-0
Fax. 532 06 52
e-mail: gerhard@ai.univie.ac.at
WWW: http://www.ai.univie.ac.at/~gerhard
----------------------------------------------------------------------------
9th EUROPEAN CONFERENCE ON MACHINE LEARNING (ECML-97)
23-26 April 1997, Prague, Czech Republic
PRELIMINARY PROGRAMME
----------------------------------------------------------------------------
Up-to-date information on the conference (including registration information)
can be found at
http://is.vse.cz/ecml97/home.html
This programme with complete abstracts of all talks and links to the
workshops is also available at
http://www.ai.univie.ac.at/ecml/programme.html
-----------------------------------------------------------------------------
--------------------
WEDNESDAY, APRIL 23:
--------------------
9.00 - 9.30 Welcome
9.30 - 10.30 INVITED TALK:
Uncertain Learning Agents
Stuart Russell, University of California, Berkeley, USA
10.30 - 11.00 Coffee Break
11.00 - 10.30 Integrated Learning and Planning Based on
Truncating Temporal Differences
Pawel Cichosz
11.30 - 12.00 Finite-Element Methods with Local Triangulation Refinement
for Continuous Reinforcement Learning Problems
Remi Munos
12.00 - 12.15 Learning and Exploitation Do Not Conflict
Under Minimax Optimality
Csaba Szepesvari
12.15 - 12.30 Exploiting Qualitative Knowledge to Enhance Skill Acquisition
Cristina Baroglio
12.30 - 14.00 Lunch
14.00 - 15.00 INVITED TALK:
Constructing and Sharing Perceptual Distinctions
Luc Steels, Free University of Brussels (VUB) and
Sony Computer Science Laboratory, Paris
15.00 - 15.30 Ibots Learn Genuine Team Solutions
Cristina Versino, Luca Maria Gambardella
15.30 - 16.00 Coffee Break
16.00 - 16.30 NeuroLinear: A System for Extracting Oblique Decision Rules
from Neural Networks
Rudy Setiono, Huan Liu
16.30 - 17.00 Learning Different Types of New Attributes by Combining the
Neural Network and Iterative Attribute Construction
Yuh-Jyh Hu
17.00 - 17.45 Commenting Session
-------------------
THURSDAY, APRIL 24:
-------------------
9.00 - 10.00 INVITED TALK:
On Prediction by Data Compression
Paul Vitanyi, CWI, Amsterdam
10.00 - 10.30 Conditions for Occam's Razor Applicability and
Noise Elimination
Dragan Gamberger, Nada Lavrac
10.30 - 11.00 Coffee Break
11.00 - 11.30 Compression-Based Pruning of Decision Lists
Bernhard Pfahringer
11.30 - 11.45 Inductive Genetic Programming with Decision Trees
Nikolay I. Nikolaev, Vanio Slavov
11.45 - 12.00 Probabilistic Incremental Program Evolution:
Stochastic Search Through Program Space
Rafal Salustowicz, Juergen Schmidhuber
12.00 - 12.30 Constructing Intermediate Concepts by Decomposition
of Real Functions
Janez Demsar, Blaz Zupan, Marko Bohanec, Ivan Bratko
12.30 - 14.00 Lunch
14.00 - 14.30 Global Data Analysis and the Fragmentation Problem in
Decision Tree Induction
Ricardo Vilalta, Gunnar Blix, Larry Rendell
14.30 - 15.00 Model Combination in the Multiple-Data-Batches Scenario
Kai Ming Ting, Boon Toh Low
15.00 - 15.30 Commenting Session
15.30 - 16.00 Coffee Break
16.00 - 17.00 Poster Session
17.00 - open ECML Community Meeting
-----------------
FRIDAY, APRIL 25:
-----------------
9.00 - 9.15 A Case Study in Loyalty and Satisfaction Research
Koen Vanhoof, Josee Bloemer, Koen Pauwels
9.15 - 9.30 Inducing and Using Decision Rules in the
GRG Knowledge Discovery System
Ning Shan, Howard J. Hamilton, Nick Cercone
9.30 - 9.45 Learning When Negative Examples Abound
Miroslav Kubat, Robert Holte, Stan Matwin
9.45 - 10.00 Search-Based Class Discretization
Luis Torgo, Joao Gama
10.00 - 10.15 Classification by Voting Feature Intervals
G"ulsen Demir"oz, H. Altay G"uvenir
10.15 - 10.30 A Model for Generalization Based on Confirmatory Induction
Nicolas Lachiche, Pierre Marquis
10.30 - 11.00 Coffee Break
11.00 - 11.30 Natural Ideal Operators in Inductive Logic Programming
Fabien Torre, Celine Rouveirol
11.30 - 12.00 Theta-subsumption for Structural Matching
Luc De Raedt, Peter Idestam-Almquist, Gunther Sablon
12.00 - 12.30 Induction of Feature Terms with INDIE
Eva Armengol, Enric Plaza
12.30 - 12.45 Metrics on Terms and Clauses
Alan Hutchinson
12.45 - 13.00 Learning Linear Constraints in Inductive Logic Programming
Lionel Martin, Christel Vrain
Afternoon off - trip and farewell party (optional; see social programme)
------------------
SATURDAY, APRIL 26:
------------------
ECML/MLNet WORKSHOPS:
WS 1: Data-Driven Learning of Natural Language Processing Tasks
WS 2: Case-Based Learning: Beyond Classification of Feature Vectors
WS 3: Learning in Dynamically Changing Domains:
Theory Revision and Context Dependence Issues
WS 4: Machine Learning and Human-Agent Interaction