Invited Papers -- String Pattern Discovery -- Applications of Regularized Least Squares to Classification Problems -- Probabilistic Inductive Logic Programming -- Hidden Markov Modelling Techniques for Haplotype Analysis -- Learning, Logic, and Probability: A Unified View -- Regular Contributions -- Learning Languages from Positive Data and Negative Counterexamples -- Inductive Inference of Term Rewriting Systems from Positive Data -- On the Data Consumption Benefits of Accepting Increased Uncertainty -- Comparison of Query Learning and Gold-Style Learning in Dependence of the Hypothesis Space -- Learning r-of-k Functions by Boosting -- Boosting Based on Divide and Merge -- Learning Boolean Functions in AC 0 on Attribute and Classification Noise -- Decision Trees: More Theoretical Justification for Practical Algorithms -- Application of Classical Nonparametric Predictors to Learning Conditionally I.I.D. Data -- Complexity of Pattern Classes and Lipschitz Property -- On Kernels, Margins, and Low-Dimensional Mappings -- Estimation of the Data Region Using Extreme-Value Distributions -- Maximum Entropy Principle in Non-ordered Setting -- Universal Convergence of Semimeasures on Individual Random Sequences -- A Criterion for the Existence of Predictive Complexity for Binary Games -- Full Information Game with Gains and Losses -- Prediction with Expert Advice by Following the Perturbed Leader for General Weights -- On the Convergence Speed of MDL Predictions for Bernoulli Sequences -- Relative Loss Bounds and Polynomial-Time Predictions for the k-lms-net Algorithm -- On the Complexity of Working Set Selection -- Convergence of a Generalized Gradient Selection Approach for the Decomposition Method -- Newton Diagram and Stochastic Complexity in Mixture of Binomial Distributions -- Learnability of Relatively Quantified Generalized Formulas -- Learning Languages Generated by Elementary Formal Systems and Its Application to SH Languages -- New Revision Algorithms -- The Subsumption Lattice and Query Learning -- Learning of Ordered Tree Languages with Height-Bounded Variables Using Queries -- Learning Tree Languages from Positive Examples and Membership Queries -- Learning Content Sequencing in an Educational Environment According to Student Needs -- Tutorial Papers -- Statistical Learning in Digital Wireless Communications -- A BP-Based Algorithm for Performing Bayesian Inference in Large Perceptron-Type Networks -- Approximate Inference in Probabilistic Models.

Algorithmic learning theory is mathematics about computer programs which learn from experience. This involves considerable interaction between various mathematical disciplines including theory of computation, statistics, and c- binatorics. There is also considerable interaction with the practical, empirical ?elds of machine and statistical learning in which a principal aim is to predict, from past data about phenomena, useful features of future data from the same phenomena. The papers in this volume cover a broad range of topics of current research in the ?eld of algorithmic learning theory. We have divided the 29 technical, contributed papers in this volume into eight categories (corresponding to eight sessions) re?ecting this broad range. The categories featured are Inductive Inf- ence, Approximate Optimization Algorithms, Online Sequence Prediction, S- tistical Analysis of Unlabeled Data, PAC Learning & Boosting, Statistical - pervisedLearning,LogicBasedLearning,andQuery&ReinforcementLearning. Below we give a brief overview of the ?eld, placing each of these topics in the general context of the ?eld. Formal models of automated learning re?ect various facets of the wide range of activities that can be viewed as learning. A ?rst dichotomy is between viewing learning as an inde?nite process and viewing it as a ?nite activity with a de?ned termination. Inductive Inference models focus on inde?nite learning processes, requiring only eventual success of the learner to converge to a satisfactory conclusion.