Discovery learning in intelligent tutoring systems -- From inductive inference to algorithmic learning theory -- A stochastic approach to genetic information processing -- On learning systolic languages -- A note on the query complexity of learning DFA -- Polynomial-time MAT learning of multilinear logic programs -- Iterative weighted least squares algorithms for neural networks classifiers -- Domains of attraction in autoassociative memory networks for character pattern recognition -- Regularization learning of neural networks for generalization -- Competitive learning by entropy minimization -- Inductive inference with bounded mind changes -- Efficient inductive inference of primitive Prologs from positive data -- Monotonic language learning -- Prudence in vacillatory language identification (Extended abstract) -- Implementation of heuristic problem solving process including analogical reasoning -- Planning with abstraction based on partial predicate mappings -- Learning k-term monotone Boolean formulae -- Some improved sample complexity bounds in the probabilistic PAC learning model -- An application of Bernstein polynomials in PAC model -- On PAC learnability of functional dependencies -- Protein secondary structure prediction based on stochastic-rule learning -- Notes on the PAC learning of geometric concepts with additional information.

This volume contains the papers that were presented at the Third Workshop onAlgorithmic Learning Theory, held in Tokyo in October 1992. In addition to 3invited papers, the volume contains 19 papers accepted for presentation, selected from 29 submitted extended abstracts. The ALT workshops have been held annually since 1990 and are organized and sponsored by the Japanese Society for Artificial Intelligence. The main objective of these workshops is to provide an open forum for discussions and exchanges of ideasbetween researchers from various backgrounds in this emerging, interdisciplinary field of learning theory. The volume is organized into parts on learning via query, neural networks, inductive inference, analogical reasoning, and approximate learning.