A Study of Good Predecessor Programs for Reducing Fitness Evaluation Cost in Genetic Programming

Good predecessor programs (GPPs) are the ancestors of the best program found in a genetic programming (GP) evolution. This paper reports on an investigation into GPPs with the ultimate goal of reducing fitness evaluation cost in tree-based GP systems. A framework is developed for gathering information about GPPs and a series of experiments is conducted on a symbolic regression problem, a binary classification problem, and a multi-class classification program with increasing levels of difficulty in different domains. The analysis of the data shows that during evolution, GPPs typically constitute less than 33% of the total programs evaluated, and may constitute less than 5%. The analysis results further shows that in all evaluated programs, the proportion of GPPs is reduced by increasing tournament size and to a less extent, affected by population size. Problem difficulty seems to have no clear influence on the proportion of GPPs.

[1]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[2]  Bernhard Sendhoff,et al.  Reducing Fitness Evaluations Using Clustering Techniques and Neural Network Ensembles , 2004, GECCO.

[3]  D. Goldberg,et al.  Don't evaluate, inherit , 2001 .

[4]  Leonardo Vanneschi,et al.  Theory and practice for efficient genetic programming , 2004 .

[5]  Leonardo Vanneschi,et al.  A new technique for dynamic size populations in genetic programming , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[6]  Matthias Fuchs,et al.  Large Populations Are Not Always The Best Choice In Genetic Programming , 1999, GECCO.

[7]  Wolfgang Banzhaf,et al.  Decreasing the Number of Evaluations in Evolutionary Algorithms by Using a Meta-model of the Fitness Function , 2003, EuroGP.

[8]  Mengjie Zhang,et al.  Applying Online Gradient Descent Search to Genetic Programming for Object Recognition , 2004, ACSW.

[9]  M. Tomassini,et al.  Saving computational effort in genetic programming by means of plagues , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[10]  L. Altenberg.  EMERGENT PHENOMENA IN GENETIC PROGRAMMING , 1994 .

[11]  David Jackson.  Fitness evaluation avoidance in Boolean GP problems , 2005, 2005 IEEE Congress on Evolutionary Computation.

[12]  Mengjie Zhang,et al.  Population Clustering in Genetic Programming , 2006, EuroGP.

[13]  Sean Luke,et al.  Population Implosion in Genetic Programming , 2003, GECCO.

[14]  D. J. Newman,et al.  UCI Repository of Machine Learning Database , 1998 .

[15]  Leonardo Vanneschi,et al.  Limiting the Number of Fitness Cases in Genetic Programming Using Statistics , 2002, PPSN.

[16]  Christopher J. Merz,et al.  UCI Repository of Machine Learning Databases , 1996 .

[17]  Sung-Bae Cho,et al.  An efficient genetic algorithm with less fitness evaluation by clustering , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[18]  P. Sen,et al.  Introduction to bivariate and multivariate analysis , 1981 .

[19]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[20]  Leonardo Vanneschi,et al.  Dynamic Size Populations in Distributed Genetic Programming , 2005, EuroGP.

[21]  Reiko Tanese,et al.  Distributed Genetic Algorithms , 1989, ICGA.

[22]  Walter Alden Tackett,et al.  Recombination, selection, and the genetic construction of computer programs , 1994 .