Coevolutionary Neural Population Models
This work provides a method for analyzing coevolutionary interactions in neural networks, which is incremental as it applies existing evolutionary models to a new context.
The authors tackled the problem of modeling evolutionary population dynamics using neural networks, and found that evolutionary game theory models can describe the behavior of these neural systems.
We present a method for using neural networks to model evolutionary population dynamics, and draw parallels to recent deep learning advancements in which adversarially-trained neural networks engage in coevolutionary interactions. We conduct experiments which demonstrate that models from evolutionary game theory are capable of describing the behavior of these neural population systems.