Solution-Locked Averages and Solution-Time Binning in Genetic Programming
Averaging data collected in multiple independent runs across generations is the standard method to study the behaviour of GP. We show that while averaging may represent with good resolution GP’s behaviour in the early stages of a run, it blurs later components of the dynamics. We propose two techniques to improve the situation: solution-locked averaging and solution-time binning. Results indicate that there are significant benefits in adopting these techniques.
KeywordsSolution Time Symbolic Regression Symbolic Regression Problem Ordinary Average Initial Rapid Growth
Unable to display preview. Download preview PDF.
- 1.Citi, L., Poli, R., Cinel, C.: High-significance averages of event-related potential via genetic programming. In: Riolo, R.L., O’Reilly, U.-M., McConaghy, T. (eds.) Genetic Programming Theory and Practice VII, Genetic and Evolutionary Computation, May 14-16, vol. 9, pp. 135–157. Springer, Ann Arbor (2009)Google Scholar
- 4.Luck, S.J.: An introduction to the event-related potential technique. MIT Press, Cambridge (2005)Google Scholar
- 5.Poli, R., Cinel, C., Citi, L., Sepulveda, F.: Reaction-time binning: a simple method for increasing the resolving power of ERP averages. Psychophysiology (Forthcoming, 2010)Google Scholar