Learnability and the Vapnik-Chervonenkis dimension
Citations
22 citations
22 citations
Cites background from "Learnability and the Vapnik-Chervon..."
...ably approximately correct learning (PAC learning, introduced by Valiant in [40]), the size of the random sample required as the training set is determined by the VC-density of the concept class rather than by its VC-dimension (see [6], Lemma 7)....
[...]
...The motivation for finding bounds on the VC-density comes from the fact that it is this quantity, rather than VC-dimension, that is actually relevant in combinatorial and algorithmic applications [6, 8, 9, 25, 26]....
[...]
22 citations
Cites background from "Learnability and the Vapnik-Chervon..."
...training sets (Cover 1965; Blumer et al. 1989 )....
[...]
...Denition 1 (Baum and Haussler 1989; Blumer et al. 1989 ) Consider the set of vectors X =fxig N i=12X N . We say that X is shattered byG if for all (y1; y2; ; yN)2 4 f 1; +1gN, there exists g2G such that yi = g(xi) for i = 1; 2; ; N....
[...]
22 citations
References
42,654 citations
40,020 citations
17,939 citations
14,948 citations
13,647 citations