Analytic Continued Fractions for Regression: A Memetic Algorithm Approach
This addresses the problem of finding compact and interpretable mathematical models for AI, particularly in regression tasks, but appears incremental as it builds on existing memetic algorithm approaches.
The authors tackled regression problems by using analytic continued fractions as a novel representation, achieving results that statistical tests showed provide a powerful and interesting new alternative for compact and interpretable models, though no concrete numbers were provided.
We present an approach for regression problems that employs analytic continued fractions as a novel representation. Comparative computational results using a memetic algorithm are reported in this work. Our experiments included fifteen other different machine learning approaches including five genetic programming methods for symbolic regression and ten machine learning methods. The comparison on training and test generalization was performed using 94 datasets of the Penn State Machine Learning Benchmark. The statistical tests showed that the generalization results using analytic continued fractions provides a powerful and interesting new alternative in the quest for compact and interpretable mathematical models for artificial intelligence.