Abstract
We introduce a method to train a bio-inspired neural network model, having the characteristics of spiking-timing-dependent interaction and learning, in a manner of supervised learning. We assume the spiking neural network model has the tendency to obey the charge conservation principle or the junction rule on a long (or the learning dynamics) time scale. The tendency makes the distribution of connectivities is determined depending on not only the incoming stimuli to input neurons but also the outgoing stimuli from output neurons as if a solution of the finite elementary method in a fluid system. We apply the learning method to several cases in simulations and find the adoption of the conservation principle exerts desired effects on the neural network learning. Finally, we discuss the significance and the drawbacks of the introduced method and compare it with the supervised learning method implemented by the artificial neural network model.
Similar content being viewed by others
References
I. Goodfellow, Y. Bengio, A. Couville, Y. Bengio, Deep Learning (MIT Press, Cambridge, 2016)
W. Gerstner, W.M. Kistler, R. Naud, Neuronal Dynamics (Cambridge University Press, New York, 2014)
J.H.R. Maunsell et al., Vis. Neurosci. 16, 1 (1999)
K.-M. Lee, E.L. Keller, J. Neurosci. 28, 2242 (2008)
H. Markram, J. Lubke, M. Frotscher, B. Sakamann, Science 275, 213 (1997)
L. Zhang, H. Tao, C. Holt, W. Harris, M.-M. Poo, Nature 95, 37 (1998)
G.-Q. Bi, M.-M. Poo, J. Neurosci. 18, 10464 (1998)
L.F. Abbott, S.B. Nelson, Nat. Neurosci. 3, 1178 (2000)
M.W. Cho, M.W. Choi, Europhys. Lett. 115, 38001 (2016)
M.W. Cho, J. Korean Phys. Soc. 71, 222 (2017)
J.J. Hopfield, Proc. Natl. Acad. Sci. USA 79, 2554 (1982)
D.H. Ackley, G. Hinton, T. Sejnowski, Cogn. Sci. 9, 147 (1985)
M.W. Cho, J. Korean Phys. Soc. 73, 1385 (2018)
M.W. Cho, M.Y. Choi, J. Korean Phys. Soc. 77, 168 (2020)
M.W. Cho, J. Korean Phys. Soc. 75, 261 (2019)
M.W. Cho, New Phys. Sae Mulli 65, 456 (2015)
M.W. Cho, New Phys. Sae Mulli 66, 786 (2016)
M.W. Cho, New Phys. Sae Mulli 69, 874 (2019)
Acknowledgements
This work was supported by the Sungshin Women’s University Research Grant of 2018-2-82-013/1.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cho, M.W. Supervised learning in a spiking neural network. J. Korean Phys. Soc. 79, 328–335 (2021). https://doi.org/10.1007/s40042-021-00254-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40042-021-00254-4