Concept class

Abstract: Introduction The Problem of Thomas Hobbes Formalistic Views of Representation \"Standing For\": Descriptive Representation \"Standing For\": Symbolic Representation Representing as \"Acting For\": The Analogies The Mandate-Independence Controversy Representing Unattached Interests: Burke Representing People Who Have Interests: Liberalism Political Representation Appendix on Etymology Notes Bibliography Index

Abstract: This paper addresses the problem of improving the accuracy of an hypothesis output by a learning algorithm in the distribution-free (PAC) learning model. A concept class is learnable (or strongly learnable) if, given access to a source of examples of the unknown concept, the learner with high probability is able to output an hypothesis that is correct on all but an arbitrarily small fraction of the instances. The concept class is weakly learnable if the learner can produce an hypothesis that performs only slightly better than random guessing. In this paper, it is shown that these two notions of learnability are equivalent. A method is described for converting a weak learning algorithm into one that achieves arbitrarily high accuracy. This construction may have practical applications as a tool for efficiently converting a mediocre learning algorithm into one that performs extremely well. In addition, the construction has some interesting theoretical consequences, including a set of general upper bounds on the complexity of any strong learning algorithm as a function of the allowed error e.

Abstract: Valiant's learnability model is extended to learning classes of concepts defined by regions in Euclidean space En. The methods in this paper lead to a unified treatment of some of Valiant's results, along with previous results on distribution-free convergence of certain pattern recognition algorithms. It is shown that the essential condition for distribution-free learnability is finiteness of the Vapnik-Chervonenkis dimension, a simple combinatorial parameter of the class of concepts to be learned. Using this parameter, the complexity and closure properties of learnable classes are analyzed, and the necessary and sufficient conditions are provided for feasible learnability.

Abstract: We consider the problem of using queries to learn an unknown concept. Several types of queries are described and studied: membership, equivalence, subset, superset, disjointness, and exhaustiveness queries. Examples are given of efficient learning methods using various subsets of these queries for formal domains, including the regular languages, restricted classes of context-free languages, the pattern languages, and restricted types of prepositional formulas. Some general lower bound techniques are given. Equivalence queries are compared with Valiant's criterion of probably approximately correct identification under random sampling.