This paper presents a study of fitness distance correlation and negative slope coefficient as measures of problem hardness for genetic programming. Advantages and drawbacks of both these measures are presented both from a theoretical and empirical point of view. Experiments have been performed on a set of well-known hand-tailored problems and “real-life-like” GP benchmarks
Vanneschi, L., Tomassini, M., Collard, P., Clergue, P. (2005). A Survey of Problem Difficulty in Genetic Programming. In 9th Congress of the Italian Association for Artificial Intelligence - AI/IA 2005: Advances in Artificial Intelligence; Milan; Italy; 21 September 2005 through 23 September 2005 Proceedings (pp.66-77). Springer [10.1007/11558590_7].
A Survey of Problem Difficulty in Genetic Programming
VANNESCHI, LEONARDO;
2005
Abstract
This paper presents a study of fitness distance correlation and negative slope coefficient as measures of problem hardness for genetic programming. Advantages and drawbacks of both these measures are presented both from a theoretical and empirical point of view. Experiments have been performed on a set of well-known hand-tailored problems and “real-life-like” GP benchmarksI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.