Title :
Initial performance comparisons for the delta coding algorithm
Author :
Mathias, Keith E. ; Whitley, L. Darrell
Author_Institution :
Dept. of Comput. Sci., Colorado State Univ., Fort Collins, CO, USA
Abstract :
Delta coding is an iterative genetic search strategy that sustains search by periodically re-initializing the population. This helps to avoid premature convergence during genetic search. Delta coding also remaps hyperspace with each iteration in an attempt to locate “easier” search spaces with respect to genetic search. Here, the optimization ability of delta coding is compared against the CHC genetic algorithm and a mutation driven stochastic hill-climbing algorithm on a suite of standard genetic algorithm test functions
Keywords :
encoding; genetic algorithms; iterative methods; search problems; stochastic processes; CHC genetic algorithm; delta coding algorithm; hyperspace; initial performance comparisons; iterative genetic search strategy; mutation driven stochastic hill-climbing algorithm; optimization ability; periodic re-initialization; population; search spaces; standard genetic algorithm test functions; Computer science; Convergence; Decoding; Genetic algorithms; Genetic mutations; Hypercubes; Iterative algorithms; Sampling methods; Stochastic processes; Testing;
Conference_Titel :
Evolutionary Computation, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the First IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1899-4
DOI :
10.1109/ICEC.1994.349911
