Analytic Continued Fractions for Regression: A Memetic Algorithm Approach

TL;DR

This paper introduces a novel regression approach using analytic continued fractions, evaluated with a memetic algorithm against various machine learning methods on 94 datasets, demonstrating promising generalization and interpretability.

Contribution

It proposes a new representation for regression problems using analytic continued fractions combined with a memetic algorithm, offering a compact and interpretable alternative.

Findings

Analytic continued fractions outperform some existing methods in generalization.

The approach yields compact models with good interpretability.

Statistical tests confirm the effectiveness of the proposed method.

Abstract

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.