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 neuro-evolution. 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 layers, and increases performance.

Connectivity, multilayer perceptron, synapse, regression
© 2021 Massachusetts Institute of Technology
2021
Massachusetts Institute of Technology
You do not currently have access to this content.