ICML'96 Preliminary Technical Program

THURSDAY July 4 8:45-9:00 Welcome address 9:00-10:00 (Plenary Session) Nir Friedman, Moises Goldszmidt "Discretizing Continuous Attributes While Learning Bayesian Networks" Seishi Okamoto, Nobuhiro Yugami "Theoretical Analysis of the Nearest Neighbor Classifier in Noisy Domains" 10:00-11:00 (Invited Speaker) Vladimir Vapnik "Statistical Theory of Generalization" 11:00-11:30: Coffee Break 11:30-13:00 (Plenary Session) Yoav Freund, Robert E. Schapire "Experiments with a New Boosting Algorithm" Tom Dietterich, Michael Kearns, Yishay Mansour "Applying the Weak Learning Framework to Understand and Improve C4.5" Eric B. Baum "Toward a Model of Mind as a Laissez-Faire Economy of Idiots" 13:00-14:30: Lunch 14:30-16:00 Parallel Session A Michele Sebag "Delaying the Choice of Bias: A Disjunctive Version Space Approach" Peter Geibel, Fritz Wysotzki "Learning Relational Concepts with Decision Trees" Werner Emde, Dietrich Wettschereck "Relational Instance-Based Learning" 14:30-16:00 Parallel Session B Rich Caruana "Algorithms and Applications for Multitask learning" Sebastian Thrun, Joseph O'Sullivan "Discovering Structure in Multiple Learning Tasks: The TC Algorithm" Tim Oates, Paul R. Cohen "Searching for Structure in Multiple Streams of Data" 14:30-16:00 Parallel Session C Mehram Sahami, Marti Hearst, Eric Saund "Applying the Multiple Cause Mixture Model to Text Categorization" Naoki Abe, Hang Li "Learning Word Association Norms Using Tree Cut Pair Models" Chris Wallace, Kevin B. Korb, Honghua Dai "Causal Discovery via MML" 16:00-16:30: Coffee Break 16:30-17:30 Parallel Session A Jukka Hekanaho "Background Knowledge in GA-based Concept Learning" Caroline Ravise, Michele Sebag "An Advanced Evolution Should Not Repeat its Past Errors" 16:30-17:30 Parallel Session B Alicia Perez "Representing and Learning Quality-Improving Planning Control Knowledge" Kang Soo Tae, Diane J. Cook "Experimental Knowledge Acquisition for Planning" 16:30-17:30 Parallel Session C Jean-Daniel Zucker, Jean-Gabriel Ganascia "Representation Changes for Efficient Learning in Structural Domains" Davide Roverso "Analogy Access by Mapping Spreading and Abstraction in Large Multifunctional Knowledge Bases" FRIDAY July 5 9:00-10:00 (Plenary Session) Kai Ming Ting "The Characterisation of Predictive Accuracy and Decision Combination" Kazuo J. Ezawa, Moninder Singh, Steven W. Norton "Learning Goal Oriented Bayesian Networks for Telecommunications Risk Management" 10:00-11:00 (Invited Speaker) Heikki Mannila "Data Mining and Machine Learning" 11:00-11:30: Coffee Break 11:30-13:00 Parallel Session A Marco Wiering, Jurgen Schmidhuber "Solving POMDPs with Levin Search and EIRA" Sridhar Mahadevan "Sensitive Discount Optimality: Unifying Discounted and Average Reward Reinforcement Learning" Remi Munos "A Convergent Reinforcement Learning Algorithm in the Continuous Case: the Finite-Element-Q Learning" 11:30-13:00 Parallel Session B Gerhard Widmer "Recognition and Exploitation of Contextual Clues via Incremental Meta-Learning" David P. Helmbold, Robert E. Schapire, Yoram Singer, Manfred K. Warmuth "On-Line Portfolio Selection Using Multiplicative Updates" Enrico Blanzieri, Patrick Katenkamp "Learning Radial Basis Function Networks On-line" 11:30-13:00 Parallel Session C Ron Kohavi, David H. Wolpert "Bias Plus Variance Decomposition for Zero-One Loss Functions" Geoffrey J. Gordon, Alberto Maria Segre "Nonparametric Statistical Methods for Experimental Evaluations of Speedup Learning" Marco Saerens "Non Mean Square Error Criteria for the Training of Learning Machines: An Estimation Theory Point of View" 13:00-14:30: Lunch 14:30-16:00 Parallel Session A Prasad Tadepalli, DoKyeong Ok "Scaling Up Average Reward Reinforcement Learning by Approximating the Domain Models and the Value Function" Justin A. Boyan, Andrew W. Moore "Learning Evaluation Functions for Large Acyclic Domains" C. Bandera, M. E. Harmon, F. J. Vico, J. M. Bravo, L. C. Baird III "Residual Q-Learning Applied to Visual Attention" 14:30-16:00 Parallel Session B C. J. C. Burges "Simplified Support Vector Decision Rules" Russell Greiner, Adam J. Grove, Alexander Kogan "Exploiting the Omission of Irrelevant Data" Leonardo Carbonara, Derek Sleeman "Improving Efficiency of Knowledge Base Refinement" 14:30-16:00 Parallel Session C Sally A. Goldman, Stephen D. Scott "A Theoretical and Empirical Study of a Noise-Tolerant Algorithm to Learn Geometric Patterns" Richard H. Lathrop "On the Learnability of the Uncomputable" Pascal Jappy, Richard Nock, Olivier Gascuel "Negative Robust Learning results for Horn Clause Programs" 16:00-16:30: Coffee Break 16:30-18:00 Parallel Session A Miroslav Kubat "Second Tier for Decision Trees" Andreas Ittner, Michael Schlosser "Non-Linear Decision Trees" Steven Donoho, Larry Rendell "Constructive Induction using Fragmentary Knowledge" 16:30-18:00 Parallel Session B Stephan Grolimund, Jean-Gabriel Ganascia "Speeding-up Nearest Neighbour Memories: The Template Tree Case Memory Organisation" Aynur Akkus, H. Altay Guvenir "k-Nearest Neighbor Classification on Feature Projections" Henry Tirri, Petri Kontkanen, Petri MyllyMaki "Probabilistic Instance-Based Learning" 16:30-18:00 Parallel Session C Joe Suzuki "Learning Bayesian Belief Networks Based on the Minimum Description Length Principle: An Efficient Algorithm Using the B&B Technique" Moninder Singh, Gregory M. Provan "Efficient Learning of Selective Bayesian Network Classifiers" Craig Boutilier, Richard Dearden "Approximating Value Trees in Structured Dynamic Programming" SATURDAY July 6 9:00-10:00 (Plenary Session) Russell Greiner, Adam J. Grove, Dan Roth "Learning Active Classifiers" Sven Koenig, Reid G. Simmons "Passive Distance Learning for Robot Navigation" 10:00-11:00 (Invited Speaker) Andrew Moore "Reinforcement learning in Factories: The Auton Project" 11:00-11:30: Coffee Break 11:30-13:00 (Plenary Session) Eduardo Perez, Larry Rendell "Learning Despite Concept Variation by Finding Structure in Attribute-Based Data" Jonathan J. Oliver, Rohan A. Baxter, Chris S. Wallace "Unsupervised Learning Using MML" Andrew R. Golding, Dan Roth "Applying Winnow to Context-Sensitive Spelling Correction" 13:00-14:30: Lunch 14:30-16:00 Parallel Session A Chandra Reddy, Prasad Tadepalli, Silvana Roncagliolo "Theory-guided Empirical Speedup Learning of Goal Decomposition Rules" Sean P. Engelson, Moshe Koppel "Identifying the Information Contained in a Flawed Theory" Henrik Bostrom "Theory Guided Induction of Logic Programs by Inference of Regular Languages" 14:30-16:00 Parallel Session B M.L. Littman, C. Szepesvari "A Generalized Reinforcement Learning Model: Convergence and Applications" Mark Pendrith, Malcolm Ryan "Actual Return Learning versus Temporal Differences: Some theoretical and experimental results" P. Goetz, S. Kumar, R. Miikkulainen "On-Line Adaptation of a Signal Predistorter through Dual Reinforcement Learning" 14:30-16:00 Parallel Session C Pedro Domingos, Michael Pazzani "Beyond Independence: Conditions for Optimality of the Simple Bayesian Classifier" Daphne Koller, Mehran Sahami "Toward Optimal Feature Selection" Huan Liu, Rudy Setiono "A Probabilistic Approach to Feature Selection - A Filter Solution" 16:00-16:30: Coffee Break 16:30-17:00 Business Meeting