************************************************************************** NEWSLETTER ON DECISION AND REASONING UNDER UNCERTAINTY Issue 99003 Editors: Salem Benferhat, Henri Prade 15.07.1999 Back issues available at http://www.ida.liu.se/ext/etai/dru/index.html ************************************************************************** To subscribe or to correct an entry from the directory of researchers temporarily located at: http://cafe.newcastle.edu.au/salem/chercheur.html please send an email to benferhat@irit.fr or prade@irit.fr This newsletter contains: 1. Technical program of UAI99 2. Call for papers of IPMU-2000 ========================================================================== 1. Technical program of UAI99 ========================================================================== Fifteenth Annual Conference on Uncertainty in Artificial Intelligence July 30 - August 1, 1999 KTH Stockholm, Sweden UAI '99 Conference Program Friday July 30, 1999 8:30 AM Welcome (Greg Cooper, Kathryn Laskey and Henri Prade) Plenary Session 1: Learning I 8:45 AM 1.Variational Learning in Mixed-State Dynamic Graphical Models - Vladimir Pavlovic, Brendan J. Frey, Thomas Huang 2.Accelerating EM: An Empirical Study - Luis E. Ortiz and Leslie P. Kaelbling 3.Model based Bayesian Exploration - Richard Dearden, Nir Friedman, David Andre Break 10:00 AM Invited Talk 1 10:20 AM Inference Networks and the Evaluation of Evidence: Alternative Analyses - David A. Schum Plenary Session 2: Utility 11:20 AM 1.Efficient Value of Information Computation - Ross D. Shachter 2.Lazy Evaluation of Symmetric Bayesian Decision Problems - Anders L Madsen, Finn V. Jensen Lunch 12:10 PM Poster session 1 1:40 PM 1.Discovering the Hidden Structure of Complex Dynamic Systems - Xavier Boyen, Nir Friedman, Daphne Koller 2.Evaluation of Distributed Intelligence on the Smart Card - Kazuo J. Ezawa, Greg Napiorkowski, Mariusz Kossarski 3.Data Analysis with Bayesian Networks - A Bootstrap Approach - Nir =46riedman, Moises, Goldszmidt, Abraham Wyner 4.Parameter priors for directed acyclic graphical models and the characterization of several probability distributions - Dan Geiger, David Heckerman 5.Faithful Approximations of Belief Functions - David Harmanec 6.On Supervised Selection of Bayesian Networks - Petri Kontkanen, Petri Myllymaki, Tomi Silander, Henry Tirri 7.Bayesian Poker - Kevin B. Korb, Ann E. Nicholson and Nathalie Jitnah 8.Learning Finite-State Controllers for Partially Observable Environments - Nicolas Meuleau, Leonid Peshkin, Kee-Eung Kim and Leslie P. Kaelbling 9.The Decision-Theoretic Interactive Video Advisor - Hien Nguyen and Peter Haddawy 10.Well defined decision scenarios - Thomas D. Nielsen and Finn V. Jensen 11.Graphical Representations of Consensus Belief - David M. Pennock and Michael P. Wellman 12.Enhancing QPNs for Trade-off Resolution - S. Renooij, L.C. van der Gaag 13.Approximate Learning in complex dynamic Bayesian networks - R. Settimi, J. Q. Smith and A. S. Gargoum 14.An Update Semantics for Defeasible Obligations - Leendert W.N. van der Torre, Yao-Hua Tan 15.Probabilistic Belief Change: Expansion, Conditioning and Constraining - =46rans Voorbraak 16.A Method for Speeding Up Value Iteration in Partially Observable Markov Decision Processes - Nevin L. Zhang, Stephen S. Lee, Weihong Zhang Break 3:40 PM Plenary Session 3: Decision 4:00 PM 1.Reasoning With Conditional Ceteris Paribus Preference Statements - Craig Boutilier, Ronen I. Brafman, Holger Hoos, David Poole 2.A hybrid approach to reasoning with partially elicited preference models - Vu Ha and Peter Haddawy 3.Qualitative Models for Decision Under Uncertainty without the Commensurability Assumption - Helene Fargier, Patrice Perny Panel 1 5:15 PM 15 Years of UAI: Where Have we Been and Where Are We Going? - Orgainized by Tod Levitt End of Friday Program 6:15 PM Banquet 7:00 PM Saturday July 31, 1999 Plenary Session 4: Finalists and Winner of Best Student Paper Award 8:30 AM 1.On the Power of Mini-Bucket Heuristics for Improved Search - Kalev Kask and Rina Dechter 2.Expected utility networks - Piero La Mura and Yoav Shoham 3.Random Algorithms for the Loop Cutset Problem - Ann Becker, Reuven Bar-Yehuda, Dan Geiger Break 9:45 AM Invited Talk 2 10:05 AM Practical uses of belief functions - Philippe Smets Plenary Session 5: Learning 11:05 AM 1.Learning Parameters and Structure of Latent Variable Models by Variational Bayes - Hagai Attias 2.Efficient Learning of Bayesian Network Structure from Massive Datasets: The ``Sparse Candidate'' Algorithm - Nir Friedman, Iftach Nachman, Dana Pe'er 11:55 AM Lunch Poster Session 2 1:20 PM 1.A Temporal Bayesian Network for Diagnosis and Prediction - G. Arroyo-Figueroa and L. Enrique Sucar 2.Artificial Decision Making in Intelligent Buildings - Boman, Davidsson, Younes 3.Causal Discovery from a Mixture of Experimental and Observational Data - Gregory F. Cooper and Changwon Yoo 4.Assessing the value of a candidate: Comparing belief functions and possibility theories - D. Dubois, M. Grabisch, H. Prade and Ph. Smets 5.Fast Learning from Sparse Data - David Maxwell Chickering and David Heckerman 6.Learning Polytrees - Sanjoy Dasgupta 7.Hybrid Probabilistic Programs: Algorithms and Complexity - Michael I. Dekhtyar, Alex Dekhtyar, V.S. Subrahmanian 8.Quantifier Elimination for Statistical Problems - Dan Geiger and Christopher Meek 9.A new theory of plan recognition - Robert P. Goldman and Christopher Geib and Christopher S. Miller 10.SPUDD: Stochastic Planning using Decision Diagrams - Jesse Hoey, Robert St-Aubin, Craig Boutilier and Alan Hu. 11.A General Algorithm for Approximate Inference and its Application to Hybrid Bayes Nets - Daphne Koller, Uri Lerner, Dragomir Angelov 12.Learning Bayesian Networks from Incomplete Data with Stochastic Search Algorithms - James W. Myers, Kathryn B. Laskey 13.Learning Bayesian Networks with Restricted Causal Interactions - Julian R. Neil, Chris S. Wallace and Kevin B. Korb 14.Learning Hidden Markov Models with Geometrical Constraints - Hagit Shatk= ay 15.A process control algorithm for concentrating mixed-waste based on Bayesian cg-networks - Robert L. Welch and Clay Smoth 16.Contextual Weak Independence in Bayesian Networks - S.K.M. Wong and C.J. Butz Break 3:20 PM Plenary Session 6: POMDP/MDP 3:45 PM 1.On the complexity of policy iteration - Yishay Mansour and Satinder Sing= h 2.A Possibilistic Model for Qualitative Sequential Decision Problems under Uncertainty in Partially Observable Environments - Sabbadin Regis 3.Approximate Planning for Factored POMDPs using Simplified Belief States - David McAllester and Satinder Singh 4.Continuous Value Function Approximation for Sequential Bidding Policies - Craig Boutilier, Moises Goldszmidt, Bikash Sabata Panel 2 5:25 PM Challenges in Decision Theoretic Planning - Organized by Craig Boutilier and Hector Geffner End of Saturday Program 6:25 PM Sunday August 1, 1999 Plenary Session 7: Applications 8:30:AM 1.Bayesian Networks for Dependability Analysis: an Application to Digital Control Reliability - Luigi Portinale, Andrea Bobbio 2.Attention-Sensitive Alerting in Computing Systems - Eric Horvitz, Andy Jacobs, David Hovel 3.How to Elicit Many Probabilities - L.C. van der Gaag, S. Renooij, C.L.M. Witteman, B. Aleman and B.G. Taal 4.An Application of Uncertain Reasoning to Requirements Engineering - Philip Barry and Kathryn Blackmond Laskey Break 10:10 AM Plenary Session 8: Representing Knowledge about Uncertain Phenomena 10:30 AM 1.SPOOK: A System for Probabilistic Object-Oriented Knowledge Representation - Avi Pfeffer, Daphne Koller, Brian Milch, Ken T. Takugasawa 2.On Transformations between Probability and Spohnian Disbelief Functions - Phan Giang, Prakash Shenoy 3.Possibilistic logic bases and possibilistic graphs - Salem Benferhat, Didier Dubois, Laurent Garcia, Henri Prade 4.On the Semantics and Automated Deduction for PLFC, a logic of possibilistic uncertainty and fuzziness - Teresa Alsinet, Llus Godo, Sandra Sandri Lunch 12:10 AM Poster session 3 1:45 PM 1.Relative Loss Bounds for On-line Density Estimation with the Exponential Family of Distributions - Katy S. Azoury and M. K. Warmuth 2.Comparing Bayesian Network Classifers - Jie Cheng, Russell Greiner 3.Loglinear models for first-order probabilistic reasoning - James Cussens 4.A Hybrid Algorithm for the Construction of Causal Models From Sparse Data - Denver Dash and Marek Druzdzel 5.Multi-objects association in perception of dynamical situation - Gruyer Dominique, V=E9ronique Berge-Cherfaoui 6.Probabilistic Latent Semantic Analysis - Thomas Hofmann 7.Estimating the Value of Computation - Michael Horsch and David Poole 8.On Quantified Linguistic Approximation - Ryszard Kowalczyk 9.Choosing Among Interpretations of Probability - Henry E. Kyburg Jr. and Choh Man Teng 10.My Brain is Full: When More Memory Helps - Christopher Lusena, Tong Li, Shelia Sittinger, Chris Wells, Judy Goldsmith 11.Representing and Combining Partially Specified CPTs - Suzanne M.Mahoney, Kathryn Blackmond Laskey 12.Solving POMDPs by Searching the Space of Finite Policies - Nicolas Meuleau, Kee-Eung Kim, Leslie Pack Kaelbling and Anthony R. Cassandra 13.Bayes Nets in Educational Assessment: Where the Numbers Come From - Robert J. Mislevy, Russell G. ALmond, Duanli Yan and Linda S. Steinberg 14.A Bayesian network classifier that combines a finite mixture model and a naive-Bayes model - Stefano Monti and Gregory F. Cooper 15.A Variational Approximation for Bayesian Networks with Discrete and Continuous Latent Variables - Kevin P. Murphy 16.Multiplicative Factorization of Noisy-Max - Masami Takikawa and Bruce D'Ambrosio 17.Time-Critical Dynamic Decision Making - Yanping Xiang and Kim-Leng Poh Break 3:45 PM Plenary Session 9: Inference 4:00 PM 1.Mixture Approximations to Bayesian Networks - Volker Tresp, Michal Haft, Reimar Hofmann 2.Inference in Multiply Sectioned Bayesian Networks with Extended Shafer-Shenoy and Lazy Propagation - Yang Xiang and Finn Jensen 3.Loopy belief propagation for approximate inference: an empirical study Kevin P. Murphy, Yair Weiss, and Michael Jordan End of Sunday Program 5:15 PM Business Meeting 5:15 PM End of Conference 6:15 PM ========================================================================== 2. Call for papers of IPMU-2000 ========================================================================== IPMU2000 -------- The 8th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems July 3 - 7, 2000 Madrid, Spain http://www.mat.upm.es/ipmu e-mail: ipmu@mat.upm.es HONORARY PRESIDENT ------------------ Lotfi A. ZADEH (University of California at Berkeley, USA) CHAIRPERSONS ------------ Bernadette BOUCHON-MEUNIER (LIP6, CNRS, Universit=E9 Paris VI, France) Julio GUTIERREZ-RIOS (Universidad Polit=E9cnica de Madrid, Spain) Luis MAGDALENA (Universidad Polit=E9cnica de Madrid, Spain) Enric TRILLAS (Universidad Polit=E9cnica de Madrid, Spain) Ronald R. YAGER (Iona College, NY, USA) The IPMU Conference is organized every two years with the aim of bringing together scientists working on various methods for the management of uncertainty in intelligent systems. This conference provides a medium for the exchange of ideas between theoreticians and practitioners using different methods to address the important issue of uncertainty. CONFERENCE SECRETARIAT ADDRESS ------------------------------ Secretar=EDa IPMU2000 Dept. Matem=E1tica=20Aplicada ETSI Telecomunicaci=F3n Universidad Polit=E9cnica de Madrid Madrid 28040 SPAIN TECHNICAL SECRETARIAT --------------------- Ultramar Express C/ Enrique Jardiel Poncela 6 Madrid 28016 SPAIN PRESENTATION ------------ We all are very likely walking towards the Era of the Soft Computing and Computing with Words when uncertainty will be adopted as a natural component of information and knowledge, and when the ancient concept of accuracy, as the essentials of mathematics and calculations, will give way to this new generation of automatic reasoning. >From the first edition, the International Conference on Information Process and Management of Uncertainty in Knowledge Based Systems (IPMU) has proven to be an ideal forum for the exchange of ideas, methods, procedures and applications among the best researchers and professionals related to fuzzy information processing and techniques, and has become one of the best Conferences of this area in the world. Next edition, the eighth, of IPMU congress (IPMU'2000) will be held in Madrid. As the controversy about the 21st century starting point continues, we are not very sure if Madrid will be hosting the first IPMU congress of 21st century or the 20th's last one, but in any case, this is not a very appropriated discussion in a fuzzy environment. The focusing of this edition does not differ very much from the spirit of the previous ones, since our main objective is to make the best we can in order to concentrate the most interesting contributions, topics and researchers in the area. However, since IPMU evolves as time goes by, some novelties may be expected as, for example, consolidation of the European Society of Fuzzy Logic and Technology (EUSFLAT), a general inventory of advances, tendencies and achievements which could yield to some conclusions where scientific and engineering efforts must be addressed to, as well as other novelties such as exhibitions of practical applications. As a matter of fact, there will not be any special topic for the eighth IPMU Conference, since we consider this occasion must constitute a very special opportunity to reflect and do some brainstorming about the role of soft computing within the field of the new technologies, once the area has reached a high degree of maturity. TOPICS OF PARTICULAR INTEREST ----------------------------- Bayesian and Probabilistic Methods, Fuzzy Methods, Theory of Evidence, Belief Networks, Possibility theory, Chaos Theory, Measures of Information and Uncertainty, Rough Sets. Non-standard Logics, Non-monotonic Logics, Default Reasoning, Approximate Reasoning, Multivalued Logics, Temporal Reasoning, Belief Updating. Knowledge Acquisition and Representation, Machine Learning, Inductive Methods, Neural Networks, Databases, Information Retrieval, Data Mining, Uncertainty in Cognition. Intelligent Systems, Fuzzy Control, Genetic Algorithms and Evolutionary Computation, Hybrid Systems, Uncertainty in Expert Systems, Decision Support Systems, Multicriteria and Group Decision Making, Pattern Recognition, Clustering, Classification, Data Analysis, Image Processing, Fuzzy Processors, Multi-media Management, Financial Engineering, Intelligent agents, Diagnostic Systems, Fuzzy Systems Design. TIME SCHEDULE AND SUBMISSION INFORMATION ---------------------------------------- * October 15, 1999: Submission of special sessions. * November 15, 1999: Submission of papers. * February 15, 2000: Notification of acceptance. * March 31, 2000: Submission of final papers. * May 15, 2000: Deadline for early registration. * July 3-7, 2000: CONFERENCE. Authors should submit four copies of full papers (6-8 pages) written in English. Papers must include title and author's name(s) and affiliation(s) on top of the first page followed by an abstract. =46ax or e-mail submissions are not accepted. Please indicate the corresponding author, with their e-mail where possible. Send papers to: Secretar=EDa IPMU2000 Dept. Matem=E1tica Aplicada ETSI Telecomunicaci=F3n Universidad Polit=E9cnica de Madrid Madrid 28040 SPAIN INTERNATIONAL PROGRAM COMMITTEE (Tentative) ------------------------------- J. AGUILAR-MARTIN(France) C. ALSINA (Spain) J. BALDWIN (U.K.) S. BARRO (Spain) J. BEZDEK ( USA) P. BONISSONE (USA) P. BOSC (France) J.L. CASTRO (Spain) M. DELGADO (Spain) D. DUBOIS (France) F. ESTEVA (Spain) M. FEDRIZZI (Italy) L. FOULLOY (France) M.A. GIL (Spain) F. GOMIDE (Brazil) A. GONZALEZ (Spain) S. GROSSBERG (USA) S. GUIASU (Canada) P. HAJEK (Czech Rep.) F. HERRERA (Spain) K. HIROTA (Japan) J. JACAS (Spain) F.V. JENSEN (Denmark) J. KACPRZYK (Poland) A. KANDEL (USA) E.P. KLEMENT (Austria) G. KLIR (USA) J. KOHLAS (Suisse) R. KRUSE (Germany) H.L. LARSEN (Denmark) R. LOPEZ DE MANTARAS(Spain) G. MAYOR (Spain) R. MESIAR(Slovakia) C. MORAGA (Germany) H. NGUYEN (USA) S. OVCHINNIKOV (USA) H. PRADE (France) A. RALESCU (USA) D. RALESCU (USA) A.F. ROCHA (Brazil) E. RUSPINI (USA) A. SAGE (USA) E. SANCHEZ (France) R. SCOZZAFAVA (Italy) G. SHAFER (USA) P. SHENOY (USA) P. SMETS (Belgium) P. SOBREVILLA (Spain) M. SUGENO (Japan) T. TERANO (Japan) I.B. TURKSEN (Canada) R. VALLEE (France) L. VALVERDE (Spain) A. VENTRE (Italy) J.L. VERDEGAY (Spain) M.A. VILA (Spain) H. ZIMMERMANN (Germany) NATIONAL ORGANIZING COMMITTEE ----------------------------- J. BOTIA J.C. CRESPO S. CUBILLO F. FERNANDEZ E. FRIAS J.M. GO=D1I R. RIAZA J.R. VELASCO LOCATION -------- Madrid, a world-famous city where Nobody is a foreigner. The capital has always known how to be nice and amiable. Its forcefulness and personality turns Madrid into an unforgettable city, and its plentiful resources of interest to tourism -nature, art, history- are rounded off extraordinarily well by a series of cities in its surroundings which are full of sights of historic interest, some of which have been included by the UNESCO in the list of places considered "world heritage": Avila, Segovia, Toledo, as well as the Monastery of El Escorial or Alcala de Henares. Madrid has admirable parks and gardens, and a large number of museums, including those in the Avenue of Art, an itinerary unique in the entire world, which includes painting, sculpture, architecture and natural beauty, set in one of the most emblematic areas of Madrid; The Paseo del Prado. It includes three of the most important museums of Spain; the Prado Museum, the Thyssen-Bornemisza Museum and the Centro de Arte Reina Sofia. The cultural panorama of Madrid is marked today by a large number of public and private cultural institutions, banks and savings banks, universities and student residences that compete in converting the cultural spirit of Madrid into a reality that is tangible as well as multifarious.