Kodratoff Y., Michalski R.S. (eds.) Machine Learning. An Artificial Intelligence Approach, Volume III

Morgan Kaufmann, 1990. — 815.As the field of machine learning enjoys unprecedented growth and attracts many new researchers, there is a need for regular summaries and comprehensive reviews of its progress. This volume is a sequel to the previous volumes of same title: Volume I appeared in 1983, Volume II in 1986. Volume III presents sample of machine learning research representative of the period between 1986 1989.
One noteworthy characteristic of that period is that a much larger portion research has been done outside of the United States, particularly in Europe. reflect his, Volume ÉÐ contains a significant number of non-U.S.A contributions. addition, this volume covers topics not covered at all or covered only sparsely the previous volumes, such as connectionist learning methods, genetic algorithms, and computational learning theory.
To provide a comprehensive representation of research, this volume drawn on several sources. Most of the chapters are directly invited contributions leading researchers in the field. Several chapters are updated and extended versions of invited presentations at the International Meeting on Advances in Learning (IMAL) held in Les Arcs, France in July 1986. These chapters are accompanied commentaries prepared by the discussants at the meeting. Finally, few chapters based on papers selected from among those presented at the 4th and 5th International Machine Learning conferences, held at the University of California at Irvine in June 1987 and the University of Michigan at Ann Arbor in June 1988, respectively.
The bibliography at the end of the book provides a comprehensive guide these and related publications. It contains over 1000 entries and refers to publications in all major ML subareas for the period 1985-1989. All the entries are using a classification of ML publications into 17 categories.Part One General Issues
Research in Machine Learning; Recent Progress, Classification of Methods, and Future Directions
Explanations, Machine Learning, and Creativity
Part Two Empirical Learning Methods
Learning Flexible Concepts: Fundamental Ideas and a Method Bases on Two-Tiered Representation
Protos: An Exemplar-Based Learning Apprentice
Probabilistic Decision Trees
Integrating Quantitative and Qualitative Discovery in the ABACUS System
Learning by Experimentation: The Operator Refinement Method
Learning Fault Diagnosis Heuristics from Device Descriptions
Conceptual Clustering and Categorization: Bridging the Gap between Induction and Causal Models
Part Three Analytical Learning Methods
LEAP: A Learning Apprentice System for VLSI Design
Acquiring General Iterative Concepts by Reformulating Explanations of Observed Examples
Discovering Algorithms from Weak Methods
OGUST: A System that Learns Using Domain Properties Expressed as Theorems
Conditional Operationality and Explanation-based Generalization
Part Four Integrated Learning Systems
The Utility of Similarity-based Learning in a World Needing Explanation
Learning Expert Knowledge by Improving the Explanations Provided by the System
Guiding Induction with Domain Theories
Knowledge Base Refinement as Improving an Incorrect and Incomplete Domain Theory
Apprenticeship Learning in Imperfect Domain Theories
Part Five Subsymbolic and Heterogenous Learning Systems
Connectionist Learning Procedures
Genetic-Algorithm-based Learning
Part Six Formal Analysis
Applying Valiant's Learning Framework to AI Concept-Learning Problems
A New Approach to Unsupervised Learning in Deterministic Environments
Bibliography of Recent Machine Learning Research (1985-1989)