Computational Learning Theory
Automatic Capacity Tuning of Very Large VC-Dimension Classifiers
Guyon, I., Boser, B., Vapnik, V.
He is now at the University of California, Berkeley.
Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods
Haussler, David, Kearns, Michael, Opper, Manfred, Schapire, Robert
In this paper we investigate an average-case model of concept learning, and give results that place the popular statistical physics and VC dimension theories of learning curve behavior in a common framework.
The VC-Dimension versus the Statistical Capacity of Multilayer Networks
The former characterizes their "Present Address: Department of Electrical Computer and System Engineering, Rensselaer Poly tech Institute, Troy, NY 12180.
The VC-Dimension versus the Statistical Capacity of Multilayer Networks
The former characterizes their "Present Address: Department of Electrical Computer and System Engineering, Rensselaer Poly tech Institute, Troy, NY 12180.
Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods
Haussler, David, Kearns, Michael, Opper, Manfred, Schapire, Robert
In this paper we investigate an average-case model of concept learning, and give results that place the popular statistical physics and VC dimension theories of learning curve behavior in a common framework.
Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods
Haussler, David, Kearns, Michael, Opper, Manfred, Schapire, Robert
In this paper we investigate an average-case model of concept learning, and give results that place the popular statistical physics and VC dimension theories of learning curve behavior in a common framework.
The VC-Dimension versus the Statistical Capacity of Multilayer Networks
The former characterizes their "Present Address: Department of Electrical Computer and System Engineering, Rensselaer Polytech Institute, Troy, NY 12180.
A training algorithm for optimum margin classifiers
Proceedings of the Fifth Annual Workshop on Computational Learning Theory 5: 144-152, 1992.
Learning Time-varying Concepts
Kuh, Anthony, Petsche, Thomas, Rivest, Ronald L.
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 by the fact that a persons face changes slowly with age and more quickly with changes in make up, hairstyle, or facial hair.
Chaitin-Kolmogorov Complexity and Generalization in Neural Networks
Pearlmutter, Barak A., Rosenfeld, Ronald
We present a unified framework for a number of different ways of failing to generalize properly.