Empirical measure of multiclass generalization performance: the K-winner machine case
Sandro Ridella, Rodolfo Zunino · IEEE Transactions on Neural Networks · 2001
Combining the K-winner machine (KWM) model with empirical measurements of a classifier's Vapnik-Chervonenkis (VC)-dimension gives two major results. First, analytical derivations refine the theory that characterizes the generalization performances of binary classifiers. Second, a straightforward extension of the theoretical framework yields bounds to the generalization error for multiclass problems.