ISSN 0869-6632 (Print)
ISSN 2542-1905 (Online)

For citation:

Lebedev A. A., Kazantsev V. B., Stasenko S. V. Study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural network. Izvestiya VUZ. Applied Nonlinear Dynamics, 2024, vol. 32, iss. 2, pp. 253-267. DOI: 10.18500/0869-6632-003092, EDN: STLCRP

This is an open access article distributed under the terms of Creative Commons Attribution 4.0 International License (CC-BY 4.0).
Full text PDF(Ru):
PDF icon and_2024-2_lebedev-et-al_253-267.pdf
(downloads: 0)
Full text PDF(En):
PDF icon and_2024_2_lebedev_et_al.pdf
(downloads: 21)
Language: 
Russian
Heading: 
Nonlinear Dynamics and Neuroscience
Article type: 
Article
UDC: 
530.182
DOI: 
10.18500/0869-6632-003092
EDN: 
STLCRP

Study of the influence of synaptic plasticity on the formation of a feature space by a spiking neural network

Autors: 
Lebedev Andrey Aleksandrovich, Lobachevsky State University of Nizhny Novgorod
Kazantsev Viktor Borisovich, Institute of Applied Physics of the Russian Academy of Sciences
Stasenko Sergey Victorovich, Lobachevsky State University of Nizhny Novgorod
Abstract: 

The purpose of this study is to study the influence of synaptic plasticity on excitatory and inhibitory synapses on the formation of the feature space of the input image on the excitatory and inhibitory layers of neurons in a spiking neural network.

Methods. To simulate the dynamics of the neuron, the computationally efficient model “Leaky integrate-and-fire” was used. The conductance-based synapse model was used as a synaptic contact model. Synaptic plasticity in excitatory and inhibitory synapses was modeled by the classical model of time dependent synaptic plasticity. A neural network composed of them generates a feature space, which is divided into classes by a machine learning algorithm.

Results. A model of a spiking neural network was built with excitatory and inhibitory layers of neurons with adaptation of synaptic contacts due to synaptic plasticity. Various configurations of the model with synaptic plasticity were considered for the problem of forming the feature space of the input image on the excitatory and inhibitory layers of neurons, and their comparison was also carried out.

Conclusion. It has been shown that synaptic plasticity in inhibitory synapses impairs the formation of an image feature space for a classification task. The model constraints are also obtained and the best model configuration is selected.

Key words: 
spiking neural network
synaptic plasticity
machine learning
image classification
Acknowledgments: 
In terms of studying model configurations when generating an indicative description from an excitatory population of neurons the work was supported by grant from the Government of the Nizhny Novgorod Region for young scientists (agreement No. 316-06-16-111а/23 from 4 july 2023), in terms of studying model configurations when generating an indicative description from an inhibitory population of neurons the work was supported by grant from the Russian Science Foundation (project No. 23-11-00134).
Reference: 
  1. Song S, Miller KD, Abbott LF. Competitive Hebbian learning through spike-timing-dependent synaptic plasticity. Nature Neuroscience. 2000;3(9):919–926. DOI: 10.1038/78829.
  2. Thorpe S, Delorme A, Van Rullen R. Spike-based strategies for rapid processing. Neural Networks. 2001;14(6–7):715–725. DOI: 10.1016/S0893-6080(01)00083-1.
  3. Loiselle S, Rouat J, Pressnitzer D, Thorpe S. Exploration of rank order coding with spiking neural networks for speech recognition. In: Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. 31 July 2005 - 04 August 2005, Montreal, QC, Canada. New York: IEEE; 2005. P. 2076–2080. DOI: 10.1109/IJCNN.2005.1556220.
  4. Yamazaki K, Vo-Ho V-K, Bulsara D, Le N. Spiking neural networks and their applications: A review. Brain Sciences. 2022;12(7):863. DOI: 10.3390/brainsci12070863.
  5. Bohte SM, Kok JN, La Poutre H. Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing. 2002;48(1–4):17–37. DOI: 10.1016/S0925-2312(01)00658-0.
  6. Markram H, Gerstner W, Sjostrom PJ. Spike-timing-dependent plasticity: a comprehensive overview. Frontiers in Synaptic Neuroscience. 2012;4:2. DOI: 10.3389/fnsyn.2012.00002.
  7. Stasenko SV, Kazantsev VB. Dynamic image representation in a spiking neural network supplied by astrocytes. Mathematics. 2023;11(3):561. DOI: 10.3390/math11030561.
  8. Stasenko SV, Kazantsev VB. Information encoding in bursting spiking neural network modulated by astrocytes. Entropy. 2023;25(5):745. DOI: 10.3390/e25050745.
  9. Stasenko SV, Mikhaylov AN, Kazantsev VB. Model of neuromorphic odorant-recognition network. Biomimetics. 2023;8(3):277. DOI: 10.3390/biomimetics8030277.
  10. Gordleeva SY, Tsybina YA, Krivonosov MI, Ivanchenko MV, Zaikin AA, Kazantsev VB, Gorban AN. Modeling working memory in a spiking neuron network accompanied by astrocytes. Frontiers in Cellular Neuroscience. 2021;15:631485. DOI: 10.3389/fncel.2021.631485.
  11. Masquelier T, Guyonneau R, Thorpe S. Spike timing dependent plasticity finds the start of repeating patterns in continuous spike trains. PLoS ONE. 2008;3(1):e1377. DOI: 10.1371/journal. pone.0001377.
  12. Guo W, Fouda ME, Eltawil AM, Salama KN. Neural coding in spiking neural networks: A comparative study for robust neuromorphic systems. Frontiers in Neuroscience. 2021;15:638474. DOI: 10.3389/fnins.2021.638474.
  13. Borgers C. Linear integrate-and-fire (LIF) neurons. In: An Introduction to Modeling Neuronal Dynamics. Vol. 66 of Texts in Applied Mathematics. Cham: Springer; 2017. P. 45–50. DOI: 10. 1007/978-3-319-51171-9_7.
  14. Bi G-Q, Poo M-M. Synaptic modifications in cultured hippocampal neurons: Dependence on spike timing, synaptic strength, and postsynaptic cell type. J. Neurosci. 1998;18(24):10464–10472. DOI: 10.1523/JNEUROSCI.18-24-10464.1998.
  15. Deng L. The MNIST database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Processing Magazine. 2012;29(6):141–142. DOI: 10.1109/MSP.2012. 2211477.
  16. Sterratt D, Graham B, Gillies A, Willshaw D. Principles of Computational Modelling in Neuroscience. Cambridge: Cambridge University Press; 2011. 390 p. DOI: 10.1017/CBO97805 11975899.
  17. Chen Y. Mechanisms of winner-take-all and group selection in neuronal spiking networks. Frontiers in Computational Neuroscience. 2017;11:20. DOI: 10.3389/fncom.2017.00020.
Received: 
05.10.2023
Accepted: 
18.11.2023
Available online: 
19.02.2024
Published: 
29.03.2024
  • 903 reads