A Runtime Analysis of Bias-invariant Neuroevolution and Dynamic Fitness Evaluation
Paul Fischer, John Alasdair Warwicker, Carsten Witt · Proceedings of the Genetic and Evolutionary Computation Conference · 2024
In the field of neuroevolution (NE), evolutionary algorithms are used to update the weights, biases and topologies of artificial neural networks (ANNs). A recent theoretical work presented the first runtime analysis of NE in a simple setting, considering a single neuron and intuitive benchmark function classes. However, this work was limited by the unrealistic settings with regard to activation functions and fitness measurements.