Colt 89

COLT '90 covers the proceedings of the Third Annual Workshop on Computational Learning Theory, sponsored by the ACM SIGACT/SIGART, University of Rochester, Rochester, New York on August 6-8, 1990. The book focuses on the processes, methodologies, principles, and approaches involved in computational learning theory. The selection first elaborates on inductive inference of minimal programs, learning switch configurations, computational complexity of approximating distributions by probabilistic automata, and a learning criterion for stochastic rules. The text then takes a look at inductive identification of pattern languages with restricted substitutions, learning ring-sum-expansions, sample complexity of PAC-learning using random and chosen examples, and some problems of learning with an Oracle. The book examines a mechanical method of successful scientific inquiry, boosting a weak learning algorithm by majority, and learning by distances. Discussions focus on the relation to PAC learnability, majority-vote game, boosting a weak learner by majority vote, and a paradigm of scientific inquiry. The selection is a dependable source of data for researchers interested in the computational learning theory.

This volume contains selected papers presented at the Eighth Logic Programming Conference, held in Tokyo, 1989. Various topics in logic programming are covered. The first paper is an invited talk by Prof. Donald Michie, Chief Scientist of the Turing Institute, entitled "Human and Machine Learning of Descriptive Concepts", and introduces various research results on learning obtained by his group. There are eleven further papers, organized into sections on reasoning, logic programming language, concurrent programming, knowledge programming, natural language processing, and applications. A paper on knowledge programming introduces a flexible and powerful tool for incorporating and organizing knowledge using hypermedia. Another paper presents the constraint logic programming language cu-Prolog, designed for combinatorial problems; the way cu-Prolog solves the constraints is based on program transformation.

This book constitutes the refereed proceedings of the 11th International Conference on Algorithmic Learning Theory, ALT 2000, held in Sydney, Australia in December 2000. The 22 revised full papers presented together with three invited papers were carefully reviewed and selected from 39 submissions. The papers are organized in topical sections on statistical learning, inductive logic programming, inductive inference, complexity, neural networks and other paradigms, support vector machines.

Illustrated with more than 200 artworks and photographs and accompanied by exhaustive technical specifications, Colt: An American Classic is an expertly written account of the firearms produced by one of the world’s best-known and easily recognized gun manufacturers.