Using Multiobjective Genetic Programming to infer logistic polynomial regression models
Andrew Hunter · European Conference on Artificial Intelligence · 2002
In designing non-linear classifiers, there are important trade-offs to be made between predictive accuracy and model comprehensibility or complexity. We introduce the use of Genetic Programming to generate logistic polynomial models, a relatively comprehensible non-linear parametric model; describe an efficient two-stage algorithm consisting of GP structure design and Quasi-Newton coefficient setting; demonstrate that Niched Pareto Multiobjective Genetic Programming can be used to discover a range of classifiers with different complexity versus trade-offs; introduce a technique to integrate a new ROC (Receiver Operating Characteristic) dominance concept into the multiobjective setting; and suggest some modifications to the Niched Pareto GA for use in Genetic Programming. The technique successfully generates classifiers with diverse complexity and performance characteristics.