T. Kowaliw and W. Banzhaf
in Morphogenetic Engineering: Toward Programmable Complex Systems,
edited by R. Doursat, H. Sayama, O. Michel, Springer Berlin Heidelberg, 2012
definitive version
chapter preprint (PDF)
BibTEX
See also this video of a talk that roughly corresponds to this material (at the ISC-PIF in 2010). You know, in case you prefer listening to reading.
In this chapter, we argue that artificial development is an appropriate means of approaching complex systems engineering. Artificial development works via the inclusion of mechanisms that enhance the evolvability of a design space. Two of these mechanisms, regularities and adaptive feedback with the environment, are discussed. We concentrate on the less explored of the two: adaptive feedback. A concrete example is presented and applied to a simple artificial problem resembling vasculogenesis. It is shown that the use of a local feedback function substantively improves the efficacy of a machine learner on the problem. Further, inclusion of this adaptive feedback eliminates the sensitivity of the machine learner to a system parameter previously shown to correspond to problem hardness.