Journal ArticleDOI
Learnability and the Vapnik-Chervonenkis dimension
Reads0
Chats0
TLDR
This paper shows 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.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.read more
Citations
More filters
Journal ArticleDOI
Exploiting label dependencies for improved sample complexity
TL;DR: This work proposes new approaches for identifying and modeling existing dependencies between labels and develops methods for identifying conditionally and unconditionally dependent label pairs; clustering them into several mutually exclusive subsets; and performing multi-label classification incorporating the discovered dependencies.
Journal ArticleDOI
Pac-learning non-recursive Prolog clauses
TL;DR: It is demonstrated that a number of syntactic generalizations of this language are hard to learn, but that the language can be generalized to clauses of constant locality while still allowing pac-learnability.
Proceedings Article
On generalization bounds, projection profile, and margin distribution
TL;DR: This work uses random projection techniques to allow the use of existing VC dimension bounds in the effective, lower, dimension of the data and develops a data dependent approach that is used to derive generalization bounds that depend on the margin distribution.
Proceedings ArticleDOI
Approximating the volume of definable sets
TL;DR: An upper bound on the precision that should be used in a Monte-Carlo integration method is given and an application to a problem of structural complexity in the Blum-Shub-Smale model of computation over the reals is described.
Journal ArticleDOI
Exact Learning of Discretized Geometric Concepts
TL;DR: An algorithm is presented that exactly learns unions of discretized axis-parallel boxes in constant dimensional space in polynomial time and a new complexity measure is introduced that better captures the complexity of the union of $m$ boxes than simply the number of boxes and the dimension.
References
More filters
Book
Computers and Intractability: A Guide to the Theory of NP-Completeness
TL;DR: The second edition of a quarterly column as discussed by the authors provides a continuing update to the list of problems (NP-complete and harder) presented by M. R. Garey and myself in our book "Computers and Intractability: A Guide to the Theory of NP-Completeness,” W. H. Freeman & Co., San Francisco, 1979.
Book
The Art of Computer Programming
TL;DR: The arrangement of this invention provides a strong vibration free hold-down mechanism while avoiding a large pressure drop to the flow of coolant fluid.
Journal ArticleDOI
Pattern Classification and Scene Analysis.
Book
Pattern classification and scene analysis
Richard O. Duda,Peter E. Hart +1 more
TL;DR: In this article, a unified, comprehensive and up-to-date treatment of both statistical and descriptive methods for pattern recognition is provided, including Bayesian decision theory, supervised and unsupervised learning, nonparametric techniques, discriminant analysis, clustering, preprosessing of pictorial data, spatial filtering, shape description techniques, perspective transformations, projective invariants, linguistic procedures, and artificial intelligence techniques for scene analysis.