Self-Adaptation of Genetic Operator Probabilities Using Differential Evolution
Fatemeh Vafaee, Peter C. Nelson · 2009
In this work a novel approach is proposed to adaptively adjust genetic operator probabilities through the adoption of a robust, real-valued optimization algorithm known as Differential Evolution (DE). We set up a series of experiments on a wide array of symbolic regression problems. The experimental results demonstrate the supremacy of our proposed method over the compared rivals both in the accuracy and reliability of the final solutions.