Abstract
Attempts have been made to realize reservoir computing by using physical materials, but they assume the stable structure of a reservoir. However, in reality, a physical reservoir suffers from malfunctions, noise, and interferences, which cause failures of neurons and disconnection of synaptic connections. Consequently dynamics of system state changes and computation performance deteriorates. In this paper, we investigate structural properties contributing to the functional robustness of a reservoir. More specifically, we analyze the relationship between structural properties of a reservoir of a Liquid State Machine and the decrease in discrimination capability in a delayed readout task when experiencing failures of connections and neurons. We apply seven types of networks which have different structural properties to a reservoir. As a result, we revealed that high modularity, structural irregularity, and high clustering coefficient are most important for an LSM to be robust against random connection and neuron failures.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Albert, R., Barabási, A.L.: Statistical mechanics of complex networks. Rev. Modern Phys. 74(1), 47 (2002)
Betzel, R.F., et al.: Generative models of the human connectome. Neuroimage 124, 1054–1064 (2016)
Dale, M., Miller, J.F., Stepney, S.: Reservoir computing as a model for in-materio computing. In: Adamatzky, A. (ed.) Advances in Unconventional Computing. ECC, vol. 22, pp. 533–571. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-33924-5_22
Erdos, P., Rényi, A.: On the evolution of random graphs. Publ. Math. Inst. Hungarian Acad. Sci. 5(1), 17–60 (1960)
Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugenics 7(7), 179–188 (1936)
Freeman, L.C.: A set of measures of centrality based on betweenness. Sociometry 35–41 (1977)
Gerstner, W., Kistler, W.M.: Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge University Press, Cambridge (2002)
Kamei, D., Wakamiya, N.: Analysis of LSM-based event detection in impulse-based wireless sensor networks. In: Proceedings of the 2018 International Symposium on Nonlinear Theory and Its Applications (NOLTA 2018), pp. 460–463 (2018)
Kerepesi, C., Szalkai, B., Varga, B., Grolmusz, V.: How to direct the edges of the connectomes: dynamics of the consensus connectomes and the development of the connections in the human brain. PLOS ONE 11(6), e0158680 (2016)
Kerepesi, C., Szalkai, B., Varga, B., Grolmusz, V.: The braingraph.org database of high resolution structural connectomes and the brain graph tools. Cogn. Neurodyn. 11(5), 483–486 (2017). https://doi.org/10.1007/s11571-017-9445-1
Lukoševičius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127–149 (2009)
Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14(11), 2531–2560 (2002)
Muldoon, S.F., Bridgeford, E.W., Bassett, D.S.: Small-world propensity and weighted brain networks. Sci. Rep. 6, 22057 (2016)
Nakajima, K., Hauser, H., Li, T., Pfeifer, R.: Information processing via physical soft body. Sci. Rep. 5, 10487 (2015)
Newman, M.E., Girvan, M.: Finding and evaluating community structure in networks. Phys. Rev. E 69(2), 026113 (2004)
Soriano, M.C., Massuti-Ballester, P., Yelo, J., Fischer, I.: Optoelectronic reservoir computing using a mixed digital-analog hardware implementation. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11731, pp. 170–174. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30493-5_18
Szalkai, B., Kerepesi, C., Varga, B., Grolmusz, V.: High-resolution directed human connectomes and the consensus connectome dynamics. PLOS ONE 14(4), e0215473 (2019)
Tanaka, G., et al.: Recent advances in physical reservoir computing: a review. Neural Netw. 115, 110–123 (2019)
Watts, D.J., Strogatz, S.H.: Collective dynamics of ‘small-world’ networks. Nature 393(6684), 440 (1998)
Acknowledgements
This study was partly supported by JSPS KAKENHI Grant Number 16H01719. Data were provided in part by the Human Connectome Project, WU-Minn Consortium (Principal Investigators: David Van Essen and Kamil Ugurbil; 1U54MH091657) funded by the 16 NIH Institutes and Centers that support the NIH Blueprint for Neuroscience Research; and by the McDonnell Center for Systems Neuroscience at Washington University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Okumura, Y., Wakamiya, N. (2020). Analysis of Reservoir Structure Contributing to Robustness Against Structural Failure of Liquid State Machine. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12397. Springer, Cham. https://doi.org/10.1007/978-3-030-61616-8_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-61616-8_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61615-1
Online ISBN: 978-3-030-61616-8
eBook Packages: Computer ScienceComputer Science (R0)