Gene expression programming is the most recent development on artificial evolutionary systems and one that brings about a considerable increase in performance due to the crossing of the phenotype threshold. For the first time in artificial evolution, with GEP, the phenotype threshold is fully crossed, allowing the unconstrained exploration of the search space. In GEP, the implementation of high-performing search operators such as point mutation, transposition and recombination, is a child’s play as any modification made in the genome always results in valid phenotypes or programs. The structural and functional organization of GEP chromosomes and the new language (Karva language) especially developed to read and express the information encoded in the chromosomes, were thoroughly presented, allowing the easy understanding and implementation of the algorithm.

Furthermore, the workings of the algorithm were analyzed step-by-step with a simple problem of symbolic regression, where entire populations were thoroughly analyzed so that the simple yet wondrous ways of evolution could be completely understood.