Are Artificial Dendrites useful in NeuroEvolution?
This work addresses the potential benefits of biologically inspired dendritic processing in neuroevolution, but it appears incremental as it builds on existing neuroevolution methods with a specific adaptation.
The study investigated whether adding a simple dendrite-inspired mechanism to neuroevolution improves performance, finding that it can be positively selected for and increases performance, particularly for connections between hidden and output layers.
The significant role of dendritic processing within neuronal networks has become increasingly clear. This letter explores the effects of including a simple dendrite-inspired mechanism into neuroevolution. The phenomenon of separate dendrite activation thresholds on connections is allowed to emerge under an evolutionary process. It is shown how such processing can be positively selected for, particularly for connections between the hidden and output layer, and increases performance.