Distance-based Kernels for Surrogate Model-based Neuroevolution
This work addresses the challenge of reducing computational costs in neuroevolution for researchers and practitioners, but it appears incremental as it focuses on comparing existing distance-based approaches.
The paper tackled the problem of optimizing neural network topologies when fitness evaluations are expensive by proposing different distance metrics for surrogate models, and compared them in a simple numerical test scenario.
The topology optimization of artificial neural networks can be particularly difficult if the fitness evaluations require expensive experiments or simulations. For that reason, the optimization methods may need to be supported by surrogate models. We propose different distances for a suitable surrogate model, and compare them in a simple numerical test scenario.