J.N. Richter and J. Paxton (USA)
Genetic Algorithms, Neural-Fuzzy-Genetic Systems, Adaptive and Optimal Control
Genetic algorithms (GAs) are powerful tools that allow engineers and scientists to find good solutions to hard computational problems using evolutionary principles. The classic genetic algorithm suffers from the configuration problem, the difficulty of choosing optimal parameter settings. Genetic algorithm literature is full of empirical tricks, techniques, and rules of thumb that enable GAs to be optimized to perform better in some way by altering the GA parameters. However these techniques are often analyzed on only a narrow set of fitness functions. This paper is a first empirical step in analyzing several parameter adaptive techniques on the unitation class of fitness functions, where fitness is a function of the number of ones in the binary genome.
Important Links:
Go Back
