Summary

Proceedings of the 2012 International Symposium on Nonlinear Theory and its Applications

2012

Session Number:B4L-D

Session:

Number:519

Optimized Temporal Multiplexing for Reservoir Computing with a Single Delay-Coupled Node

Hazem Toutounji,  Johannes Schumacher,  Gordon Pipa,  

pp.519-522

Publication Date:

Online ISSN:2188-5079

DOI:10.15248/proc.1.519

PDF download (468.1KB)

The computational performance of reservoir computers based on a single delay-coupled node is critically dependent on the temporal multiplexing of input to the reservoir. Here we present an optimization of the temporal multiplexing by means of optimizing virtual node distance to maximize the response of the delay-coupled system to stimulation. After demonstrating the analytical approach, we discuss how the optimization has a single optimum (concave problem), and illustrate the improvement of the reservoir computer's performance. To this end we predict a NARMA-10 time series and show that optimizing temporal multiplexing reduces the normalized root mean squared error by ∼ 8%.

[1] D. V. Buonomano and W. Maass, “State-dependent computations: spatiotemporal processing in cortical networks,” Nat. Rev. Neurosci., vol.10, no. 2, 113-25, 2009.

[2] H. Jaeger, “The echo state approach to analysing and training recurrent neural networks,” Tech. report, 2001.

[3] W. Maass, T. Natschläger, and H. Markram, “Real-time computing without stable states: a new framework for neural computation based on perturbations,” Neural Comput., vol.14, no. 11, 2531-60, 2002.

[4] L. Appeltant, M. C. Soriano, G. Van der Sande, J. Danckaert, S. Massar, J. Dambre, B. Schrauwen, C. R. Mirasso, and I. Fischer, “Information processing using a single dynamical node as complex system,” Nat. Commun., vol.2, 468+, 2011.

[5] M. Mackey, L. Glass, “Mackey-Glass equation,” Scholarpedia, 4, no. 12, 6908, 2009.

[6] G. Daoudal and D. Debanne, “Long-term plasticity of intrinsic excitability : learning rules and mechanisms,” Learn Mem., Nov-Dec ;10(6):456-65, 2003.

[7] A. Lazar, G. Pipa, and J. Triesch, “SORN: a self-organizing recurrent neural network,” Front. Comput. Neurosci., vol.3, no. October, 23, 2009.

[8] H. Toutounji and G. Pipa, “Neuronal plasticity makes recurrent networks noise robust by generating intrinsic noise,” in prep.