 |
    |
Statistics-Based Adaptive Non-uniform Mutation for Genetic Algorithms
Shengxiang Yang
Department of Mathematics and Computer Science
University of Leicester
University Road
Leicester LE1 7RH, UK
s.yang@mcs.le.ac.uk
Abstract. A statistics-based adaptive non-uniform mutation (SANUM) is presented for genetic algorithms (GAs), within which the probability that each gene will subject to mutation is learnt adaptively over time and over the loci. SANUM uses the statistics of the allele distribution in each locus to adaptively adjust the mutation probability of that locus. The experiment results demonstrate that SANUM performs persistently well over a range of typical test problems while the performance of traditional mutation operators with fixed rates greatly depends on the problems. SANUM represents a robust adaptive mutation that needs no advanced knowledge about the problem landscape.
LNCS 2724, p. 1618 ff.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2003