Buy the Book

  Home
  News
  Author
  Q&A
  Tutorials
  Downloads
  GEP Biblio
  Contacts

  Visit Gepsoft

 

© C. FERREIRA, 2002 (Terms of Use) (Terms of Use) ISBN: 9729589054

Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence

Gene expression programming
 
Gene expression programming was invented by myself in 1999 (Ferreira 2001), and is the inevitable development of GAs and GP, incorporating both the idea of simple, linear chromosomes of fixed length used in GAs and the ramified structures of different sizes and shapes used in GP.

GEP uses the same kind of diagram representation of GP, but the entities evolved by GEP (expression trees) are the expression of a linear genome. Therefore, with GEP, the second evolutionary threshold – the phenotype threshold – is crossed, creating a new range of possibilities in evolutionary computation.

The pivotal insight of GEP consisted in the invention of chromosomes capable of representing any tree. For that purpose I created a new language – Karva language – to read and express the information encoded in GEP chromosomes.

Furthermore, the structure of chromosomes was designed to allow the creation of multiple genes, each coding for a smaller program or sub-expression tree. It is worth emphasizing that GEP is the only genetic algorithm with multiple genes. Indeed, the creation of more complex individuals composed of multiple genes is extremely simplified in truly functional genotype/phenotype systems. In fact, after their inception, these systems seem to catapult themselves into higher levels of complexity and countless new ideas are waiting to be explored. In this book we will encounter some of these rather complex entities like, for instance, multicellular individuals with different cells expressing different combinations of genes or adaptive genotype/phenotype artificial neural networks.

The basis for all this novelty resides on the revolutionary structure of GEP genes. The simple but plastic structure of these genes not only allows the encoding of any conceivable program but also allows their efficient evolution. Due to this structural organization, a very powerful set of genetic operators can be easily implemented and used to search very efficiently the solution space. As in nature, the genetic operators of gene expression programming always produce valid structures and therefore are remarkably suited to creating genetic diversity.

In the next chapter we are going to learn about the structural and functional organization of GEP chromosomes; how the language of the chromosomes is translated into the language of the expression trees; how the chromosomes work as genotype and the expression trees as phenotype; and how an individual program is created, matured, and reproduced, leaving offspring with new properties, thus, capable of adaptation.

Home | Contents | Previous | Next