Evolution, Learning, and Culture: Computational Metaphors for Adaptive Algorithms
Richard K. Belew
Computer Science and Engineering Department (C-014),
University of California at San Diego, La Jolla, CA 92093, USA
Abstract
Potential interactions between connectionist learning systems and algorithms modeled after evolutionary adaptation are becoming of increasing interest. In a recent short and elegant paper Hinton and Nowlan extend a version of Holland's genetic algorithm (GA) to consider ways in which the evolution of species and the learning of individuals might interact [17]. Their model is valuable both because it provides insight into potential interactions between the natural processes of evolution and learning and as a potential bridge between the artificial questions of efficient and effective machine learning using the GA and connectionist networks. This paper begins by describing the GA and Hinton and Nowlan's simulation. We then analyze their model, use this analysis to explain its nontrivial dynamical behaviors, and consider the sensitivity of the simulation to several key parameters.
Our next step is to interpose a third adaptive system---culture---between the learning of individuals and the evolution of populations. Culture accumulates the "wisdom'' of individuals' learning beyond the lifetime of any one individual but adapts more responsively than the pace of evolution allows. We describe a series of experiments in which the most minimal notion of culture has been added to the Hinton and Nowlan model, and we use this experience to comment on the functional value of culture, and similarities between and interactions among these three classes of adaptive systems.
