文档介绍：A STUDY OF IC PROGRAMMING VARIABLE
POPULATION SIZE FOR DYNAMIC OPTIMIZATION PROBLEMS
Leonardo Vanneschi
Department of Informatics, Systems munication (.), University of Milano-a, Milan, Italy
******@
Giuseppe u
Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA), Lugano, Switzerland
******@
Keywords: ic Programming, Variable Size Population, Dynamic Optimization.
Abstract: A new model of ic Programming with variable size population is presented in this paper and applied to
the reconstruction of target functions in dynamic environments (. problems where target functions change
with time). The suitability of this model is tested on a set of benchmarks based on some well known symbolic
regression problems. Experimental results confirm that our variable size population model finds solutions of
similar quality to the ones found by standard ic Programming, but with a smaller amount puta-
tional effort.
1 INTRODUCTION 2004). Simply speaking, it works by shrinking the
population when fitness is improving and increasing
Many real-world problems are anchored in dy- its size, by adding new ic material, when the
namic environments, where some element of the evolution stagnates. Our hypothesis is that when the
problem domain, typically the target, changes with target function changes, evolution of the current p