Spiking Neural PID Controllers
A PID controller is a simple and general-purpose way of providing responsive control of dynamic systems with reduced overshoot and oscillation. Spiking neural networks offer some advantages for dynamic systems control, including an ability to adapt, but it is not obvious how to alter such a control network’s parameters to shape its response curve. In this paper we present a spiking neural PID controller: a small network of neurons that mimics a PID controller by using the membrane recovery variable in Izhikevich’s simple model of spiking neurons to approximate derivative and integral functions.
KeywordsSpiNNaker neural networks PID controllers
Unable to display preview. Download preview PDF.
- 1.Dayan, P., Abbott, L.F.: Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems, 1st edn. The MIT Press (2001)Google Scholar
- 3.Gerstner, W., Kistler, W.M.: Spiking Neuron Models, 1st edn. Cambridge University Press (2002)Google Scholar
- 7.Izhikevich, E.M.: Dynamical Systems in Neuroscience: The Geometry of Excitability and Bursting (Computational Neuroscience), 1st edn. The MIT Press (2006)Google Scholar
- 8.Jin, X., Furber, S.B., Woods, J.V.: Efficient modelling of spiking neural networks on a scalable chip multiprocessor, pp. 2812–2819 (June 2008)Google Scholar
- 9.Rast, A.D., Khan, M.M., Jin, X., Plana, L.A., Furber, S.B.: A universal abstract-time platform for real-time neural networks. In: Proceedings of the 2009 International Joint Conference on Neural Networks, IJCNN 2009, pp. 3378–3385. IEEE Press, Piscataway (2009)Google Scholar
- 10.Rast, A.D., Jin, X., Galluppi, F., Plana, L.A., Patterson, C., Furber, S.: Scalable event-driven native parallel processing: the SpiNNaker neuromimetic system. In: Proceedings of the 7th ACM International Conference on Computing Frontiers, CF 2010, pp. 21–30. ACM, New York (2010)Google Scholar