These experiments are designed to test whether average generalization performance can surpass the worst-case bounds obtained from formal learning theory using the Vapnik-Chervonenkis dimension (Blumer et al., 1989). We indeed find that, in some cases, the average generalization is significantly better than the VC bound: the approach to perfect performance is exponential in the number of examples m, rather than the 11m result of the bound. In other cases, we do find the 11m behavior of the VC bound, and in these cases, the numerical prefactor is closely related to prefactor contained in the bound.

These experiments are designed to test whether average generalization performance can surpass the worst-case bounds obtained from formal learning theory using the Vapnik-Chervonenkis dimension (Blumer et al., 1989). We indeed find that, in some cases, the average generalization is significantly better than the VC bound: the approach to perfect performance is exponential in the number of examples m, rather than the 11m result of the bound. In other cases, we do find the 11m behavior of the VC bound, and in these cases, the numerical prefactor is closely related to prefactor contained in the bound.

These experiments are designed to test whether average generalization performance can surpass the worst-case bounds obtained from formal learning theory using the Vapnik-Chervonenkis dimension (Blumer et al., 1989). We indeed find that, in some cases, the average generalization is significantly better than the VC bound: the approach to perfect performance is exponential in the number of examples m, rather than the 11m result of the bound. In other cases, we do find the 11m behavior of the VC bound, and in these cases, the numerical prefactor is closely related to prefactor contained in the bound.

We present a unified framework for a number of different ways of failing to generalize properly.

Raleigh, NC 27695-7914 Abstract We apply the theory of Tishby, Levin, and Sol1a (TLS) to two problems. First we analyze an elementary problem for which we find the predictions consistent with conventional statistical results. Second we numerically examine the more realistic problem of training a competitive net to learn a probability density from samples. We find TLS useful for predicting average training behavior.. 1 TLS APPLIED TO LEARNING DENSITIES Recently a theory of learning has been constructed which describes the learning of a relation from examples (Tishby, Levin, and Sol1a, 1989), (Schwarb, Samalan, Sol1a, and Denker, 1990). The original derivation relies on a statistical mechanics treatment of the probability of independent events in a system with a specified average value of an additive error function. The resulting theory is not restricted to learning relations and it is not essentially statistical mechanical.

This work extends computational learning theory to situations in which concepts vary over time, e.g., system identification of a time-varying plant. We have extended formal definitions of concepts and learning to provide a framework in which an algorithm can track a concept as it evolves over time. Given this framework and focusing on memory-based algorithms, we have derived some PACstyle sample complexity results that determine, for example, when tracking is feasible. We have also used a similar framework and focused on incremental tracking algorithms for which we have derived some bounds on the mistake or error rates for some specific concept classes. 1 INTRODUCTION The goal of our ongoing research is to extend computational learning theory to include concepts that can change or evolve over time. For example, face recognition is complicated bythe fact that a persons face changes slowly with age and more quickly with changes in make up, hairstyle, or facial hair.

This symposium was very successful and was perhaps the most unusual of the spring symposia this year. It brought together for the first time distinguished researchers from many diverse disciplines to discuss and share results on a particular topic of mutual interest. The disciplines included machine learning, computational learning theory, computer vision, pattern recognition, perceptual psychology, statistics, information theory, theoretical computer science, and molecular biology, with the involvement of the latter group having lead to a joint session with the AI and Molecular Biology symposium.

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.See also: SpringerLinkMachine Learning, 5 (2), 197-227

Valiant’s learnability model is extended to learning classes of concepts defined by regions in Euclidean space E”. 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 sufftcient conditions are provided for feasible learnability.JACM, 36 (4), 929-65

MIT Press.