Algorithmic Learning Theory 11th International Conference, ALT 2000 Sydney, Australia, December 11-13, 2000 Proceedings

This book constitutes the refereed proceedings of the 11th International Conference on Algorithmic Learning Theory, ALT 2000, held in Sydney, Australia in December 2000.The 22 revised full papers presented together with three invited papers were carefully reviewed and selected from 39 submissions. The papers are organized in topical sections on statistical learning, inductive logic programming, inductive inference, complexity, neural networks and other paradigms, support vector machines.

INVITED LECTURES.- Extracting Information from the Web for Concept Learning and Collaborative Filtering.- The Divide-and-Conquer Manifesto.- Sequential Sampling Techniques for Algorithmic Learning Theory.- REGULAR CONTRIBUTIONS.- Towards an Algorithmic Statistics.- Minimum Message Length Grouping of Ordered Data.- Learning From Positive and Unlabeled Examples.- Learning Erasing Pattern Languages with Queries.- Learning Recursive Concepts with Anomalies.- Identification of Function Distinguishable Languages.- A Probabilistic Identification Result.- A New Framework for Discovering Knowledge from Two-Dimensional Structured Data Using Layout Formal Graph System.- Hypotheses Finding via Residue Hypotheses with the Resolution Principle.- Conceptual Classifications Guided by a Concept Hierarchy.- Learning Taxonomic Relation by Case-based Reasoning.- Average-Case Analysis of Classification Algorithms for Boolean Functions and Decision Trees.- Self-duality of Bounded Monotone Boolean Functions and Related Problems.- Sharper Bounds for the Hardness of Prototype and Feature Selection.- On the Hardness of Learning Acyclic Conjunctive Queries.- Dynamic Hand Gesture Recognition Based On Randomized Self-Organizing Map Algorithm.- On Approximate Learning by Multi-layered Feedforward Circuits.- The Last-Step Minimax Algorithm.- Rough Sets and Ordinal Classification.- A note on the generalization performance of kernel classifiers with margin.- On the Noise Model of Support Vector Machines Regression.- Computationally Efficient Transductive Machines.