Robust Gene Expression Programming
Year: 2011
Type: conference-paper
Abstract: Genetic/evolutionary methods are frequently used to deal with complex adaptive systems. The classic example is a Genetic Algorithm. A Genetic Algorithm uses a simple linear representation for possible solutions to a problem. This is usually a bit vector. Unfortunately, the natural representation for many problems is a tree structure. In order to deal with these types of problems many evolutionary methods make use of tree structures directly. Gene Expression Programming is a new, popular evolutionary technique that deals with these types of problems by using a linear representation for trees. In this paper we present and evaluate Robust Gene Expression Programming (RGEP). This technique is a simplification of Gene Expression Programming that is equally efficient and powerful. The underlying representation of a solution to a problem in RGEP is a bit vector as in Genetic Algorithms. It has fewer and simpler operators than those of Gene Expression Programming. We describe the basic technique, discuss its advantages over related methods, and evaluate its effectiveness on example problems.
Source: Procedia Computer Science
Authors: Noah Ryan, David Hibler
Institution: Christopher Newport University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W1973890821