Valiant Examples

Applying Valiant's Learning Framework to AI Concept Learning Problems

Parameterized Complexity Theory

Parameterized complexity theory is a recent branch of computational complexity theory that provides a framework for a refined analysis of hard algorithmic problems. The central notion of the theory, fixed-parameter tractability, has led to the development of various new algorithmic techniques and a whole new theory of intractability. This book is a state-of-the-art introduction to both algorithmic techniques for fixed-parameter tractability and the structural theory of parameterized complexity classes, and it presents detailed proofs of recent advanced results that have not appeared in book form before. Several chapters are each devoted to intractability, algorithmic techniques for designing fixed-parameter tractable algorithms, and bounded fixed-parameter tractability and subexponential time complexity. The treatment is comprehensive, and the reader is supported with exercises, notes, a detailed index, and some background on complexity theory and logic. The book will be of interest to computer scientists, mathematicians and graduate students engaged with algorithms and problem complexity.

Machine Learning

Machine Learning: An Artificial Intelligence Approach, Volume III presents a sample of machine learning research representative of the period between 1986 and 1989. The book is organized into six parts. Part One introduces some general issues in the field of machine learning. Part Two presents some new developments in the area of empirical learning methods, such as flexible learning concepts, the Protos learning apprentice system, and the WITT system, which implements a form of conceptual clustering. Part Three gives an account of various analytical learning methods and how analytic learning can be applied to various specific problems. Part Four describes efforts to integrate different learning strategies. These include the UNIMEM system, which empirically discovers similarities among examples; and the DISCIPLE multistrategy system, which is capable of learning with imperfect background knowledge. Part Five provides an overview of research in the area of subsymbolic learning methods. Part Six presents two types of formal approaches to machine learning. The first is an improvement over Mitchell's version space method; the second technique deals with the learning problem faced by a robot in an unfamiliar, deterministic, finite-state environment.