Workshop on Applications of Descriptional Complexity
	   to Inductive, Statistical, and Visual Inference

			Sunday, July 10, 1994
			  Rutgers University
		      New Brunswick, New Jersey

	 Held in Conjunction with the Eleventh International
       Conference on Machine Learning (ML94, July 11-13, 1994)
	  and the Seventh Annual Conference on Computational
	     Learning Theory (COLT94, July 12-15, 1994).


			 PRELIMINARY PROGRAM

1:45 - 1:50pm	Welcome

1:50 - 2:35pm	Keynote Talk: Asymptotically Optimal Complexity 
		Criteria, Andrew Barron, Yale University

2:35 - 3:05pm	Machine Size Selection for Optimal Generalization,
		Changfeng Wang and Santosh S. Venkatesh, 
		University of Pennsylvania

3:05 - 3:35pm	On-Line Learning Based on the Extended Stochastic
		Complexity, Kenji Yamanishi, NEC Research Institute

3:35 - 4:00pm	Break

4:00 - 4:30pm	On-Line Stochastic Prediction and MDL Principle,
		Joe Suzuki, Osaka University

4:30 - 5:00pm	Macromolecular Sequence Analysis via Algorithmic Mutual
		Information, Aleksandar Milosavljevic, Argonne National
		Laboratory

5:00 - 5:30pm	On Infinite Sequences (Almost) as Easy as Pi,
		Jose Balcazar, Ricard Gavalda, Universitat Politecnica
		de Catalunya, and Montesrrat Hermo, Universidad del
		Pais Vasco

5:30 - 7:30pm	Dinner

7:30 - 8:00pm	A Machine Learning Model and Learning Complexity
		Measures Based upon Decision Theory, Toshiyasu
		Matsushima and Shigeichi Hirasawa, Waseda University

8:00 - 8:30pm	Inferring Reduced Ordered Decision Graphs of Minimal
		Description Length, Arlindo L. Oliveira and Alberto
		Sangiovanni-Vincentelli, University of California,
		Berkeley

8:30 - 9:00pm	MDL-heuristics in Inductive Logic Programming Revised,
		Matevz Kovacic, University of Ljubljana

9:00 - 9:30pm	Analogy as a Description Minimization Principle,
		Antoine Cornuejols, Universite de Paris-sud