Heterochrony and Evolvability in Neural Network Development

Recent studies in evolutionary computation have focused on using developmental processes together with genetic algorithms in order to achieve more complex designs. Although several models have been proposed, their growth dynamics, and their interactions with evolutionary algorithms are still poorly understood. One particularly neglected concept in artificial developmental systems is heterochrony — how evolution affects development by changing the timing and rate of developmental events. In this paper we attempt to address this issue by analyzing heterochronic changes in a well known artificial developmental model — the cellular encoding model — by using an heterochrony framework by Alberch et al. We have conducted experiments by evolving networks to solve a boolean problem, and analyzed heterochronic changes in both successful and unsuccessful runs. Our findings show that the cellular encoding model, due to its properties, strongly affects the developmental dynamics and the heterochronic changes that occur during evolution. Our experiments also show that hypermorphic changes (a kind of heterochronic occurrence) lead to greater evolvability in successful runs