Kybernetika 34 no. 4, 467-472, 1998

Construction of nonlinear discrimination function based on the MDL criterion

Manabu Sato, Mineichi Kudo, Jun Toyama and Masaru Shimbo


Although a nonlinear discrimination function may be superior to linear or quadratic classifiers, it is difficult to construct such a function. In this paper, we propose a method to construct a nonlinear discrimination function using Legendre polynomials. The selection of an optimal set of Legendre polynomials is determined by the MDL (Minimum Description Length) criterion. Results using many real data show the effectiveness of this method.