Deceptive and Other Functions of Unitation as Bayesian Networks
Ole J. Mengshoel, David E. Goldberg, David C. Wilkins · 1998
Deceptive and other functions of uni- tation have been considered in order to understand which tness functions are hard and which are easy for genetic algorithms to optimize. This paper focuses on genetic algorithm tness functions represented as Bayesian networks. We investigate onemax, trap, and hill functions of unitation when converted into Bayesian networks. Among other things, this paper shows that Bayesian networks can be deceptive. 1 Introduction The notion of deception was introduced in order to system- atically investigate the conditions under which GA schema processing may lead a GA away from tness optima [Goldberg, 1987]. Functions of unitation were later discussed in connection with deceptive functions. A function of unitation (or bit-counting function) is dened over a bit string. It depends on the number of ones in the bit string, and not their positions. There are several advantages to such arti- cial functions, notably their ease of specication and analysis ...