This book considers the question of the reliability of scientific methods. One method of inquiry can be said to be more reliable than another if it eventually arrives at the truth in more possible circumstances than the other method can. Kelly begins with a discussion of the philosophical significance of reliability, examines the reliability of computable methods, provides a general, topological perspective on reliable inference by "ideal" agents, and investigates the possibility of reliable enquiry in the face of theory-laden evidence and incommensurability. The text is extensively and amusingly illustrated and assumes only introductory knowledge of basic logic and computability theory.
This illustrated work searches for the answers to such questions as whether standard methodological recommendations help or hinder the reliability of inquiry. It uses techniques and concepts drawn from formal learning theory, topology and the theory of computability.
