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.
@article{arxiv.1807.07839,
title = {Distance-based Kernels for Surrogate Model-based Neuroevolution},
author = {Jörg Stork and Martin Zaefferer and Thomas Bartz-Beielstein},
journal= {arXiv preprint arXiv:1807.07839},
year = {2018}
}
Comments
4 pages, 1 figure. This publication was accepted to the Developmental Neural Networks Workshop of the Parallel Problem Solving from Nature 2018 (PPSN XV) conference