Measuring Neutrality of Fitness Landscapes Based on the Nei’s Standard Genetic Distance

In recent years, not only ruggedness but also neutrality has been recognized as an important feature of a fitness landscape for genetic search. Since the traditional theories based on the schema theory are not useful for problems including neutrality, new theoretical guidelines should be developed for effective genetic search. This research direction has been introduced almost for ten years, but the progress is not very fast. For instance, only a few methods have been proposed or tested for measuring neutrality on the problem to be solved. In this paper, we propose the use of the Nei’s standard genetic distance, which originates from population genetics, for measuring the neutrality of a landscape. Several computer simulations are conducted by using a standard genetic algorithm in order to investigate the validity of the proposed approach. The terraced NK landscape, which is a popular test function in this field, is adopted for a test function. The results suggest to us that the Nei’s genetic distance in natural evolution is a reliable method for measuring neutrality in artificial evolution after minor modifications.