Algorithmic Learning Theory: 15th International Conference, ALT 2004, Padova, Italy, October 2-5, 2004. Proceedings

Abstract

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 fields 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 Infience, Approximate Optimization Algorithms, Online Sequence Prediction, S- tistical Analysis of Unlabeled Data, PAC Learning and Boosting, Statistical - pervisedLearning,LogicBasedLearning,andQueryandReinforcementLearning. 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 first dichotomy is between viewing learning as an indefinite process and viewing it as a finite activity with a defined termination. Inductive Inference models focus on indefinite learning processes, requiring only eventual success of the learner to converge to a satisfactory conclusion.