Learning and Reasoning with Complex Representations

This book constitutes the thoroughly revised and refereed post-workshop documentation of two international workshops held in conjunction with the Pacific Rim International Conference on Artificial Intelligence, PRICAI'96, in Cairns, Australia, in August 1996.
The volume presents 14 revised full papers togehter with two invited contributions and two introductory surveys particularly commissioned for this book. Among the topics addressed are computational learning, commonsense reasoning, constraint logic programming, fuzzy reasoning, vague data, inductive inference, belief revision, action theory, uncertainty, and probabilistic diagnosis.

Inhalt
Inductive constraint logic programming: An overview.- Some approaches to reasoning with incomplete and changing information.- Curried least general generalization: A framework for higher order concept learning.- Approximate validity.- Inductive theories from equational systems.- The role of default representations in incremental learning.- Learning stable concepts in a changing world.- Inducing complex spatial descriptions in two dimensional scenes.- A framework for learning constraints: Preliminary report.- Induction of constraint logic programs.- Belief network algorithms: A study of performance based on domain characterisation.- A Group Decision and Negotiation Support System for argumentation based reasoning.- From belief revision to design revision: Applying theory change to changing requirements.- Using histories to model observations in theories of action.- Modelling inertia in action languages.- Combinatorial interpretation of uncertainty and conditioning.- Probabilistic diagnosis as an update problem.- Cooperative combination of default logic and autoepistemic logic.