Open AccessBook
An Introduction to Computational Learning Theory
Michael Kearns,Umesh Vazirani +1 more
Reads0
Chats0
TLDR
The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata is described.Abstract:
The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata by experimentation appendix - some tools for probabilistic analysis.read more
Citations
More filters
Journal ArticleDOI
Searching for interacting features in subset selection
Zheng Zhao,Huan Liu +1 more
TL;DR: This paper takes up the challenge to design a special data structure for feature quality evaluation, and to employ an information-theoretic feature ranking mechanism to efficiently handle feature interaction in subset selection.
Book ChapterDOI
Toward Attribute Efficient Learning of Decision Lists and Parities
TL;DR: This work considers two well-studied problems regarding attribute efficient learning: learning decision lists and learning parity functions and gives the first polynomial time algorithm for learning parity on a superconstant number of variables with sublinear sample complexity.
Journal Article
Hardness of Learning Halfspaces with Noise.
TL;DR: In this paper, it was shown that weak proper agnostic learning of halfspaces is NP-hard and that the problem is intractable in the presence of random classification noise.
Book ChapterDOI
A theory of inductive query answering
TL;DR: In this article, a decomposition of a Boolean query Q into k sub-queries Q/sub i/ = q/sub A/spl and/Q/sub M/ that are the conjunction of a monotonic and an anti-monotonic predicate is presented.