Neuroevolutionary algorithms driven by neuron coverage metrics for semi-supervised classification
Roberto Santana, Iván Hidalgo-Cenalmor, Unai Garciarena, Alexander Mendiburu, Jose Antonio Lozano · 2023
In this paper, we address the question of how to evolve neural networks for semi-supervised problems. We introduce neuroevolutionary approaches that exploit unlabeled instances by using neuron coverage metrics computed on the neural network architecture encoded by each candidate solution. In our neuroevolutionary approach, we define fitness functions that combine classification accuracy computed on labeled examples and neuron coverage metrics evaluated using unlabeled examples. Our results show that the use of neuron coverage metrics helps neuroevolution to become less sensitive to the scarcity of labeled data, and can lead in some cases to a more robust generalization of the learned classifiers.