Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
The Simple Genetic Algorithm: Foundations and Theory
The Simple Genetic Algorithm: Foundations and Theory
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Crossover, Macromutationand, and Population-Based Search
Proceedings of the 6th International Conference on Genetic Algorithms
Schemata evolution and building blocks
Evolutionary Computation
Real royal road functions-where crossover provably is essential
Discrete Applied Mathematics - Special issue: Boolean and pseudo-boolean funtions
Hi-index | 0.00 |
Using an exact coarse-grained formulation of the dynamics of a GA we investigate in the context of a tunable family of "modular" fitness landscapes under what circumstances one would expect recombination to be "useful". We show that this depends not only on the fitness landscape and the state of the population but also on the particular crossover mask under consideration. We conclude that rather than ask when recombination is useful or not one needs to ask - what crossover masks are useful. We show that the answer to this is when the natural "building blocks" of the landscape are compatible with the "building blocks" defined by the crossover mask.