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
Journal ArticleDOI
A polynomial time algorithm that learns two hidden unit nets
TL;DR: An algorithm is given that probably almost correctly (PAC) learns this class of functions realizable by feedforward linear threshold nets with n input units, two hidden units each of zero threshold, and an output unit in polynomial time.
Journal ArticleDOI
The Power of Self-Directed Learning
Sally A. Goldman,Robert H. Sloan +1 more
TL;DR: Tight bounds are given on the complexity of self-directed learning for the concept classes of monomials, monotone DNF formulas, and axis-parallel rectangles in {0, 1, $$\ldots $$, n − 1}d.
How well do bayes methods work for on-line prediction of {+- 1} values?
David Haussler,A. Barron +1 more
TL;DR: This work looks at sequential classification and regression problems in which {+- 1}-labeled instances are given on-line, one at a time, and for each new instance, before seeing the label, the learning system must either predict thelabel, or estimate the probability that the label is +1.
Journal ArticleDOI
Learning in the limit with lattice-structured hypothesis spaces
TL;DR: It is shown that any class of languages is a lattice class iff it is TxtEx-learnable consistently, conservatively, set-drivenly, and strongly monotonically.
Patent
Facet classification neural network
TL;DR: In this paper, a multilayered neural network (160) consisting of an input node (162), a plurality of difference nodes (164) in a first layer, a minimum node (170), a perceptron nodes (166), in a second layer and an output node (168).
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.