Multiobjectivization for classifier parameter tuning

Abstrakt

We present a multiobjectivization approach to the parameter tuning of RBF networks and multilayer perceptrons. The approach works by adding two new objectives - maximization of kappa statistic and minimization of root mean square error--to the originally single-objective problem of minimizing the classification error of the model.

We show the performance of the multiobjectivization approach on five datasets.

Klíčová slova

• Multiobjective optimization
• classification
• machine learning
• evolutionary algorithm
• multiobjectivization
• parameter tuning