Class binarization to neuroevolution for multiclass classification

Abstract Multiclass classification is a fundamental and challenging task in machine learning. The existing techniques of multiclass can be categorized as (1) decomposition into binary (2) extension from (3) hierarchical classification. Decomposing set classifications that efficiently solved by using classifiers, called class binarization, which popular technique for Neuroevolution, general powerful evolving the structure weights neural networks, has been successfully applied to In this paper, we apply binarization neuroevolution algorithm, NeuroEvolution Augmenting Topologies (NEAT), are used generate networks We propose new method applies Error-Correcting Output Codes (ECOC) design strategies on ECOC compared with One-vs-One One-vs-All three well-known datasets Digit , Satellite Ecoli . analyse their performance four aspects degradation, accuracy, evolutionary efficiency, robustness. results show NEAT performs high accuracy low variance. Specifically, it shows significant benefits flexible number classifiers strong