Gene Expression Programming: A Survey [Review Article]
Abstract
Gene Expression Programming (GEP) is a popular and established evolutionary algorithm for automatic generation of computer programs. In recent decades, GEP has undergone rapid advancements and developments. A number of enhanced GEPs have been proposed to date and the real world applications that use them are also multiplying fast. In view of the steadfast growth of GEP and its importance to both the academia and industry, here a review on GEP is considered. In particular, this paper presents a comprehensive review on the recent progress of GEP. The state-of-the-art approaches of GEP, with enhanced designs from six aspects, i.e., encoding design, evolutionary mechanism design, adaptation design, cooperative co-evolutionary design, constant creation design, and parallel design, are presented. The theoretical studies and intriguing representative applications of GEP are given. Finally, a discussion of potential future research directions of GEP is also provided.
Authors: Jinghui Zhong, Liang Feng, Yew-Soon Ong
Published in: IEEE Computational Intelligence Magazine (2017)