In this paper we propose a novel data–driven kernel automatically determined by the training examples. Basically, it is built by combining a finite set of linearly independent functions, namely generalized terminated ramp functions, each depending on a pair of training data. When working in the Tikhonov regularization framework, the unique free parameter to be optimized is the regularizer, representing a trade-off between empirical error and smoothness of the solution
Terminated Ramp: a data-driven kernel
Merler, Stefano;Jurman, Giuseppe
2005-01-01
Abstract
In this paper we propose a novel data–driven kernel automatically determined by the training examples. Basically, it is built by combining a finite set of linearly independent functions, namely generalized terminated ramp functions, each depending on a pair of training data. When working in the Tikhonov regularization framework, the unique free parameter to be optimized is the regularizer, representing a trade-off between empirical error and smoothness of the solutionFile in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
