Algorithmic Learning Theory

Editors' Introduction.- Editors' Introduction.- Invited Papers.- Mathematics Based on Learning.- Data Mining with Graphical Models.- On the Eigenspectrum of the Gram Matrix and Its Relationship to the Operator Eigenspectrum.- In Search of the Horowitz Factor: Interim Report on a Musical Discovery Project.- Learning Structure from Sequences, with Applications in a Digital Library.- Regular Contributions.- On Learning Monotone Boolean Functions under the Uniform Distribution.- On Learning Embedded Midbit Functions.- Maximizing Agreements and CoAgnostic Learning.- Optimally-Smooth Adaptive Boosting and Application to Agnostic Learning.- Large Margin Classification for Moving Targets.- On the Smallest Possible Dimension and the Largest Possible Margin of Linear Arrangements Representing Given Concept Classes Uniform Distribution.- A General Dimension for Approximately Learning Boolean Functions.- The Complexity of Learning Concept Classes with Polynomial General Dimension.- On the Absence of Predictive Complexity for Some Games.- Consistency Queries in Information Extraction.- Ordered Term Tree Languages which Are Polynomial Time Inductively Inferable from Positive Data.- Reflective Inductive Inference of Recursive Functions.- Classes with Easily Learnable Subclasses.- On the Learnability of Vector Spaces.- Learning, Logic, and Topology in a Common Framework.- A Pathology of Bottom-Up Hill-Climbing in Inductive Rule Learning.- Minimised Residue Hypotheses in Relevant Logic.- Compactness and Learning of Classes of Unions of Erasing Regular Pattern Languages.- A Negative Result on Inductive Inference of Extended Pattern Languages.- RBF Neural Networks and Descartes' Rule of Signs.- Asymptotic Optimality of Transductive Confidence Machine.- An Efficient PAC Algorithm forReconstructing a Mixture of Lines.- Constraint Classification: A New Approach to Multiclass Classification.- How to Achieve Minimax Expected Kullback-Leibler Distance from an Unknown Finite Distribution.- Classification with Intersecting Rules.- Feedforward Neural Networks in Reinforcement Learning Applied to High-Dimensional Motor Control.