Operator equalisation is a recent bloat control technique that allows accurate control of the program length distribution during a GP run. By filtering which individuals are allowed in the population, it can easily bias the search towards smaller or larger programs. This technique achieved promising results with different predetermined target length distributions, using a conservative program length limit. Here we improve operator equalisation by giving it the ability to automatically determine and follow the ideal length distribution for each stage of the run, unconstrained by a fixed maximum limit. Results show that in most cases the new technique performs a more efficient search and effectively reduces bloat, by achieving better fitness and/or using smaller programs. The dynamics of the self adaptive length distributions are briefly analysed, and the overhead involved in following the target distribution is discussed, advancing simple ideas for improving the efficiency of this new technique.
12th European Conference on Genetic Programming (EuroGP-2009), April 2009
Cited by
Year 2013 : 1 citations
Nguyen QU, Nguyen XH, O'Neill M, McKay RI, Phong DN (2013). On the roles of semantic locality of crossover in genetic programming. Information Sciences, 10.1016/j.ins.2013.02.008.
Year 2012 : 1 citations
Quang Uy N, Xuan Hoai N, O'Neill M, McKay RI, Phonge DN (2012). On the roles of semantic locality of crossover in genetic programming. Information Sciences.
Year 2011 : 4 citations
Kronberger G, Kommenda M, Affenzeller M (2011). Overfitting detection and adaptive covariant parsimony pressure for symbolic regression. In Proc Genetic and Evolutionary Computation Conference (GECCO 2011), 631–638.
Nguyen QU (2011). Examining Semantic Diversity and Semantic Locality of Operators in Genetic Programming. PhD Thesis. School of Computer Science and Informatics, University College Dublin.
Spector L (2011). Towards Practical Autoconstructive Evolution: Self-Evolution of Problem-Solving Genetic Programming Systems. In Genetic Programming Theory and Practice VIII, 17-33.
Trujillo L (2011). Genetic programming with one-point crossover and subtree mutation for effective problem solving and bloat control. Soft Computing - A Fusion of Foundations, Methodologies and Applications 15(8): 1551–1567.
Year 2010 : 3 citations
Poli R, Vanneschi L, Langdon WB, McPhee NF (2010). Theoretical results in genetic programming: the next ten years? Genetic Programming and Evolvable Machines 11(3-4): 285-320.
Nguyen QU, McKay B, O"Neill M, Nguyen XH (2010). Self-Adapting Semantic Sensitivities for Semantic Similarity Based Crossover. CEC 2010, pp. 4034-4040.
Dignum S, Poli R (2010). Sub-tree Swapping Crossover and Arity Histogram Distributions. In Proc 13th European Conference on Genetic Programming (EuroGP-2010), 38-49.