Evolutionary computation (EC) is inspired by the mechanisms of biological evolution. With algorithmic improvements and increasing computing resources EC has discovered creative and innovative solutions to challenging practical problems. This paper evaluates how today's EC compares to biological evolution and how it may fall short. A small number of well-accepted characteristics of biological evolution are considered: openendedness, major transitions in organizational structure, neutrality and genetic drift, multiobjectivity, complex genotype-to-phenotype mappings, and coevolution. EC exhibits many of these to some extent but more can be achieved by scaling up with available computing and by emulating biology more carefully. In particular, EC diverges from biological evolution in three key respects: It is based on small populations and strong selection, it typically uses direct genotype-to-phenotype mappings, and it does not achieve major organizational transitions. These shortcomings suggest a roadmap for future EC research, and point to gaps in our understanding of how biology discovers major transitions. Advances in these areas can lead to EC that approaches the complexity and flexibility of biology, and can serve as an executable model of biological processes.

PDF

Nature Machine Intelligence, 3:9-15, 2021.

@article{Miikkulainen:natmachint21, title={A Biological Perspective on Evolutionary Computation}, author={Risto Miikkulainen and Stephanie Forrest}, volume={3}, journal={Nature Machine Intelligence}, month={ }, pages={9-15}, url="http://nn.cs.utexas.edu/?miikkulainen-forrest:natmachint21", year={2021} }