Function optimization using cartesian genetic programming

Abstract

In function optimization one tries to find a vector of real numbers that optimizes a complex multi-modal fitness function. Although evolutionary algorithms have been used extensively to solve such problems, genetic programming has not. In this paper, we show how Cartesian Genetic Programming can be readily applied to such problems. The technique can successfully find many optima in a standard suite of benchmark functions. The work opens up new avenues of research in the application of genetic programming and also offers an extensive set of highly developed benchmarks that could be used to compare the effectiveness of different GP methodologies.