论文信息 - Results on learnability and the Vapnik-Chervonenkis dimension

Results on learnability and the Vapnik-Chervonenkis dimension

The problem of learning a concept from examples in a distribution-free model is considered. The notion of dynamic sampling, wherein the number of examples examined can increase with the complexity of the target concept, is introduced. This method is used to establish the learnability of various concept classes with an infinite Vapnik-Chervonenkis (VC) dimension. An important variation on the problem of learning from examples, called approximating from examples, is also discussed. The problem of computing the VC dimension of a finite concept set defined on a finite domain is considered.<<ETX>>

[1] Vladimir Vapnik,et al. Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[2] J. Rissanen,et al. Modeling By Shortest Data Description* , 1978, Autom..

[3] D. Pollard. Convergence of stochastic processes , 1984 .

[4] Leslie G. Valiant,et al. A theory of the learnable , 1984, STOC '84.

[5] David Haussler,et al. Classifying learnable geometric concepts with the Vapnik-Chervonenkis dimension , 1986, STOC '86.

[6] Leslie G. Valiant,et al. On the learnability of Boolean formulae , 1987, STOC.

[7] M. Kearns,et al. Recent Results on Boolean Concept Learning , 1987 .

[8] Leslie G. Valiant,et al. A general lower bound on the number of examples needed for learning , 1988, COLT '88.

[9] Uzi Vishkin,et al. On Finding a Minimum Dominating Set in a Tournament , 1988, Theor. Comput. Sci..

[10] David Haussler,et al. Equivalence of models for polynomial learnability , 1988, COLT '88.

[11] Ronald L. Rivest,et al. Inferring Decision Trees Using the Minimum Description Length Principle , 1989, Inf. Comput..