Alexander Sorin, Tenkasi Ramabadran, et al.
ICASSP 2004
We show that the VC-dimension of a smoothly parameterized function class is not less than the dimension of any manifold in the parameter space, as long as distinct parameter values induce distinct decision boundaries. A similar theorem was published recently and used to introduce lower bounds on VC-dimension for several cases (Lee, Bartlett, & Williamson, 1995). This theorem is not correct, but our theorem could replace it for those cases and many other practical ones.
Alexander Sorin, Tenkasi Ramabadran, et al.
ICASSP 2004
Stéphane H. Maes, Dan Chazan, et al.
ICSLP 2000
Tenkasi Ramabadran, Alexander Sorin, et al.
ICASSP 2004
Yevgeni Litvin, Israel Cohen, et al.
Signal Processing