Finding Similarity Functions for Classification with Genetic Programming: Preliminary Results
Juan Guzman-Trampe, Nareli Cruz-Cortés, Daniel Ortíz-Arroyo · VBN Forskningsportal (Aalborg Universitet) · 2012
In this paper we propose a Genetic Programming algorithm designed with a coevolutive scheme for classi cation problems. Our algorithm searches for similarity functions that are applied to compare pairs of objects from a supervised sample. The output of these functions can be used in similarity-based classi ers.