English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We address the problem of learning feedback control where the controller is anetwork constructed solely of deterministic spiking neurons. In contrast toprevious investigations that were based on a spike rate model of the neuron,the control signal here is determined by the precise temporal positions ofspikes generated by the output neurons of the network. We model the problemformally as a hybrid dynamical system comprised of a closed loop between aplant and a spiking neuron network. We derive a novel synaptic weight updaterule via which the spiking neuron network controller learns to hold processvariables at desired set points. The controller achieves its learning objectivebased solely on access to the plant's process variables and their derivativeswith respect to changing control signals; in particular, it requires nointernal model of the plant. We demonstrate the efficacy of the rule byapplying it to the classical control problem of the cart-pole (invertedpendulum) and a model of fish locomotion. Experiments show that the proposedcontroller has a stability region comparable to a traditional PID controller,its trajectories differ qualitatively from those of a PID controller, and inmany instances the controller achieves its objective using very sparse spiketrain outputs.

Learning Feedforward and Recurrent Deterministic Spiking Neuron Network Feedback Controllers