Abstract
The crucial feature of liquid state machines (LSM) is memory which is necessary to the convert spatio-temporal input patterns and their sequences scattered in time into multidimensional representation in the form of instant neuronal activity. In this work, we utilize a methodology for exact estimation of LSM memory ability and to find parameters of the LSM “liquid” (the chaotic spiking neural network) optimal from viewpoint of memory depth using genetic algorithm. We applied this technique to chaotic networks of leaky integrate-and-fire neurons with adaptive threshold. The result of the optimization was rather unexpected – best memory was demonstrated by an ensemble of unconnected neurons more corresponding to metaphor of “gas” than “liquid”. This result compels to revise the traditional view on liquid state machines and efficiency of spiking neural networks playing the role of “liquid” in it.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Maass, W.: Liquid state machines: motivation, theory and applications. World Sci. Rev. 189, 1–21 (2010)
Tanaka, G., et al.: Recent advances in physical reservoir computing: a review. Neural Netw. 115, 100–123 (2019)
Kiselev, M., Ivanitsky, A., Lavrentyev, A.: Comparison of memory mechanisms based on adaptive threshold potential and short-term synaptic plasticity. In: Kryzhanovsky, B., et al. (eds.) Advances in Neural Computation, Machine Learning, and Cognitive Research V. Studies in Computational Intelligence, vol. 1008, pp. 334–343. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-91581-0_44
Huang, C., Resnik, A., Celikel, T., Endlitz, B.: Adaptive spike threshold enables robust and temporally precise neuronal encoding. PLoS Comput. Biol. 12(6), e1004984 (2016)
Bellec, G., Salaj, D., Subramoney, A., Legenstein, R., Maas, W.: Long short-term memory and learning-to-learn in networks of spiking neurons. In: Proceedings NIPS, Montréal, pp. 787–797 (2018)
Greff, K., Srivastava, R.K., Koutník, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28(10), 2222–2232 (2015)
Merolla, P.A., Arthur, J.V., Alvarez-Icaza, R.: A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345(6197), 668–673 (2014)
Davies, M., et al.: Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38(1), 82–99 (2018)
Grishanov, N.V., et al.: Neuromorphic processor altai for energy-efficient computing. Nanoindustry Russia 96, 531–538 (2019)
Szatmary, B., Izhikevich, E.: Spike-timing theory of working memory. PLoS Comput. Biol. 6(8), e1000879 (2010)
Kiselev, M., Ivanov, A., Ivanov, D.: Approximating conductance-based synapses by current-based synapses. In: Kryzhanovsky, B., et al. (eds.) Advances in Neural Computation, Machine Learning, and Cognitive Research IV. Studies in Computational Intelligence, vol. 925, pp. 394–402. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-60577-3_47
Cui, H., Liu, X., Li, L.: The architecture of dynamic reservoir in the echo state network. Chaos Interdiscipl. J. Nonlinear Sci. 22(3), 033127 (2012)
Acknowledgments
This work was supported by the Kaspersky and conducted at Kaspersky infrastructure.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kiselev, M., Lavrentyev, A. (2023). “GAS” Instead of “Liquid”: Which Liquid State Machine is Better?. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research VI. NEUROINFORMATICS 2022. Studies in Computational Intelligence, vol 1064. Springer, Cham. https://doi.org/10.1007/978-3-031-19032-2_49
Download citation
DOI: https://doi.org/10.1007/978-3-031-19032-2_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19031-5
Online ISBN: 978-3-031-19032-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)