Learnability and the Vapnik-Chervonenkis dimension
Citations
27 citations
27 citations
Cites background from "Learnability and the Vapnik-Chervon..."
...There are a variety of reasons for the gap between the the observed accuracy and the equation (Blumer et al., 1989) on the PAC model....
[...]
...The curve from (Blumer et al., 1989) is for δ = 0.05 ------------------------------------- Insert Figure 1 About Here -------------------------------------...
[...]
26 citations
Cites background or methods from "Learnability and the Vapnik-Chervon..."
...Using principles of PAC-learning (Blumer et al. 1989), this number of samples is expected to have an upper bound that is polynomial regardless of the distribution....
[...]
...Using principles of PAC-learning [4], this number of samples is expected to have an upper bound that is polynomial regardless of the distribution....
[...]
...The number of samples required to achieve an error rate on the true positives was shown to be much smaller in practice than the upper bound suggested by the VC dimension of the problem (Blumer et al. 1989)....
[...]
...) This would entail, by a theorem in [4], that 13 ǫ (2 ln 1 ǫ +ln 1 δ ) trials are sufficient to learn the correct window with probability...
[...]
...It is straightforward to prove that the Vapnik-Chervonenkis dimension, or VC-dimension, of this problem is 2, and that therefore, the number of examples required to learn this interval with probability at least 1 − δ and error at most is at most (13/ )(2 ln 1/ + ln 1/δ) (Blumer et al. 1989)....
[...]
26 citations
26 citations
References
42,654 citations
40,020 citations
17,939 citations
14,948 citations
13,647 citations