Results on learnability and the Vapnik-Chervonenkis dimension
Linial, N.
Mansour, Y.
Rivest, R.L.
IBM Almaden Res. Center, San Jose, CA;
This paper appears in: Foundations of Computer Science, 1988., 29th Annual Symposium on
Publication Date: 24-26 Oct 1988
On page(s): 120-129
Meeting Date: 10/24/1988 - 10/26/1988
Location: White Plains, NY, USA
ISBN: 0-8186-0877-3
References Cited: 14
INSPEC Accession Number: 3328822
DOI: 10.1109/SFCS.1988.21930
Posted online: 2002-08-06 15:59:57.0
Abstract
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
Index Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
