Journal ArticleDOI
Learnability and the Vapnik-Chervonenkis dimension
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
Proceedings ArticleDOI
On learning discretized geometric concepts
TL;DR: An online learning algorithm that learns unions of discretized axis-parallel rectangles in a constant dimensional space in polynomial time and a bounded version of the finite injury priority method to construct algorithms for learning several classes of rectangles.
Book ChapterDOI
Lower bounds on learning decision lists and trees
TL;DR: In this paper, it was shown that decision trees are not PAC-learnable and that decision lists can not be learned as efficiently as k-decision lists and decision trees, thus disproving a claim in a popular textbook.
Proceedings ArticleDOI
Learning privately with labeled and unlabeled examples
TL;DR: In this paper, the authors show that the labeled sample complexity of private semi-supervised learners is characterized by the VC dimension of the concept class, and that the unlabeled sample complexity is as big as the representation length of domain elements.
Journal ArticleDOI
Fast vertex guarding for polygons with and without holes
TL;DR: This paper observes that, since minimum visibility decompositions for simple polygons have only O(n^2) sinks (i.e., cells of minimal visibility) (Bose et al., 2000), the running time of the algorithm can be further improved to O( n^3), and shows that it can attain approximation factors of O(loglogopt) forsimple polygons and O((1+log(h+1))log opt) for polygons with holes.
Proceedings ArticleDOI
Knowledge Infusion: In Pursuit of Robustness in Artificial Intelligence
TL;DR: In knowledge infusion rules are learned from the world in a principled way so that sub- sequent reasoning using these rules will also be principled, and subject only to errors that can be bounded in terms of the inverse of the effort invested in the learning process.
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.