Learnability and the Vapnik-Chervonenkis dimension
Citations
40 citations
Cites background or methods from "Learnability and the Vapnik-Chervon..."
...[16] showed that for a wide range of classes F , an efficient algorithm for solving the search version of the consistency problem for F is suf-...
[...]
...When k = 1, this is the problem of learning a single halfspace, or that of training a simple perceptron, for which efficient algorithms are known in the PAC model [16], and in the equivalence query model [47]; in both cases the algorithms work without membership queries....
[...]
40 citations
Cites background from "Learnability and the Vapnik-Chervon..."
...For example, an efficient loading algorithm is needed for the proper PAC (probably approximately correct) learnability ( Blumer, Ehrenfeucht, Haussler, & Warmuth, 1989 ) besides the polynomial VC-dimension that the most common neural network models possess (Anthony & Bartlett, 1999; Roychowdhury, Siu, & Orlitsky, 1994; Vidyasagar, 1997)....
[...]
40 citations
40 citations
40 citations
References
42,654 citations
40,020 citations
17,939 citations
14,948 citations
13,647 citations