Michael O’Neill

Per-Node Activation Function Evolution in Indirectly Encoded Substrates: Solvability, Limits, and Emergent Diversity

Biological neurons achieve computational diversity through specialized types: tonic, bursting, adapting, and fast-spiking cells coexist within the same circuit. Artificial neural networks, by contrast, apply a single activation function uniformly to all nodes, which limits what they can represent. We show that this uni...