Abstract
In this study, we propose a discrete time vector-matrix model of a pulse neuron and novel supervised learning rules. We assumed that the synaptic connections of the neuron model are characterized by linear dynamic behavior. A distinctive feature of the considered approach is that for the training of the neuron model we do not adjust the synaptic weights, instead we adapt the impulse responses of the synaptic connections.
We propose two types of supervised learning rules. They are driven by the values of the total postsynaptic potential or by the time moments when the output pulses are emitted. The quantitative changes in the values of the impulse responses are proportional to the values of the matrix of binary vectors that fix the recent time history of input pulse trains. We demonstrate the properties of rules by computer simulation of pulsed neural networks that mimic linear dynamic reference systems.
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
References
Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)
Grüning, A., Bohte, S.M.: Spiking neural networks: principles and challenges. In: Proceedings of 22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2014), Bruges (Belgium), 23–25 April 2014. Louvain-La-Neuve (2014). i6doc.com
Ponulak, F., Kasiński, A.: Introduction to spiking neural networks: information processing, learning and applications. Acta Neurobiol. Exp. 71, 409–433 (2011)
Abbott, L.F., DePasquale, B., Memmesheimer, R.-M.: Building functional networks of spiking model neurons. Nat. Neurosci. 19(3), 350–355 (2016)
Memmesheimer, R.-M., Rubin, R., Ölveczky, B.P., Sompolinsky, H.: Learning precisely timed spikes. Neuron 82(4), 925–938 (2014). https://doi.org/10.1016/j.neuron.2014.03.026
Ponulak, F., Kasinski, A.: Supervised learning in spiking neural networks with ReSuMe: sequence learning, classification, and spike shifting. Neural Comput. 22(2), 467–510 (2010). https://doi.org/10.1162/neco.2009.11-08-901
Mohemmed, A., Schliebs, S., Matsuda, S., Kasabov, N.: SPAN: spike pattern association neuron for learning spatio-temporal spike patterns. Int. J. Neural Syst. 22(4), 1–17 (2012). https://doi.org/10.1142/S0129065712500128
Yu, Q., Tang, H., Tan, K.C., Li, H.: Precise-spike-driven synaptic plasticity: learning hetero-association of spatiotemporal spike patterns. PLoS ONE 8(11), 1–16 (2013). https://doi.org/10.1371/journal.pone.0078318
Gardner, B., Grüning, A.: Supervised learning in spiking neural networks for precise temporal encoding. PLoS ONE 11(8), 1–28 (2016). https://doi.org/10.1371/journal.pone.0161335
Bondarev, V.: Vector-matrix models of pulse neuron for digital signal processing. In: Cheng, L., Liu, Q., Ronzhin, A. (eds.) ISNN 2016. LNCS, vol. 9719, pp. 647–656. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-40663-3_74
Bondarev, V.: Pulse neuron learning rules for processing of dynamical variables encoded by pulse trains. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V. (eds.) NEUROINFORMATICS 2017. SCI, vol. 736, pp. 53–58. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-66604-4_8
Maass, W., Markram, H.: Synapses as dynamic memory buffers. Neural Netw. 15, 155–161 (2002)
Rusu, C.V., Florian, R.V.: A new class of metrics for spike trains. Neural Comput. 26(2), 306–348 (2014). https://doi.org/10.1162/NECO_a_00545
Bondarev, V.N., Smetanina, T.I.: Digital pulse neuron model for processing of wave accelerometer sensor signals. Sistemy Kontrolya Okruzhayuschey Sredy. 8(28), 16–23 (2017). (in Russian)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Bondarev, V. (2018). Pulse Neuron Supervised Learning Rules for Adapting the Dynamics of Synaptic Connections. In: Huang, T., Lv, J., Sun, C., Tuzikov, A. (eds) Advances in Neural Networks – ISNN 2018. ISNN 2018. Lecture Notes in Computer Science(), vol 10878. Springer, Cham. https://doi.org/10.1007/978-3-319-92537-0_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-92537-0_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92536-3
Online ISBN: 978-3-319-92537-0
eBook Packages: Computer ScienceComputer Science (R0)