Spikes that count: rethinking spikiness in neurally embedded systems

TitleSpikes that count: rethinking spikiness in neurally embedded systems
Publication TypeJournal Article
Year of Publication2004
AuthorsSaggie K, Keinan A, Ruppin E

Spiky neural networks are widely used in neural modeling, due to their biological relevance and high computational power. In this paper we investigate the usage of spiking dynamics in embedded artificial neural networks, that serve as a control mechanism for evolved autonomous agents performing a counting task. The synaptic weights and spiking dynamics are evolved using a genetic algorithm. We compare evolved spiky networks with evolved McCulloch–Pitts networks, while confronting new questions about the nature of “spikiness” and its contribution to the neurocontroller's processing. We show that in a memory-dependent task, network solutions that incorporate spiking dynamics can be less complex and easier to evolve than networks involving McCulloch–Pitts neurons. We identify and rigorously characterize two distinct properties of spiking dynamics in embedded agents: spikiness dynamic influence and spikiness functional contribution.