The Genetic Algorithm as a Discovery Engine

Publisher Summary This chapter puts forward the view that evolutionary algorithms together with the assemble-and-test methodology can be regarded as a discovery engine or creative machine for new designs. The chapter suggests that new principles may be discovered by examining a series of evolved designs, in this case, for arithmetic logic circuits. The chapter examines the concept of the space of all circuit representations but observes that similar ideas may well carry over to the general field of design. The human-designed algebras that form subsets of the space of all representations both for binary and multiple-valued systems are analogous to small “pools” of human principles, and by employing the blind evolutionary technique new principles may be discovered. The chapter looks at the difficult problem of principle extraction from evolved data. The chapter ends on a hopeful note that the process of learning new principles from a blind evolutionary process is just a matter of time.