Abstract
The article presents a method for implementing incremental learning on a compartmental spiking neuron model. The training of one neuron with the possibility of forming new classes was chosen as an incremental learning scenario. During the training, only a new sample was used, without knowledge of the entire previous training samples. The results of experiments on the Iris dataset are presented, demonstrating the applicability of the chosen strategy for incremental learning on a compartmental spiking neuron model.
Similar content being viewed by others
REFERENCES
Gepperth, A. and Hammer, B., Incremental learning algorithms and applications, European Symposium on Artificial Neural Networks (ESANN), Bruges, Belgium, 2016. https://hal.science/hal-01418129/.
Kukin, K. and Sboev, A., Comparison of learning methods for spiking neural networks, Opt. Mem. Neural Networks, 2015, vol. 24, pp. 123–129. https://doi.org/10.3103/S1060992X15020095
Sinyavskiy, O.Y. and Kobrin, A.I., Generalized stochastic spiking neuron model and extended spike response model in spatial-temporal pulse pattern detection task, Opt. Mem. Neural Networks, 2010, vol. 19, pp. 300–309. https://doi.org/10.3103/S1060992X10040077
Lobo, J.L., Lana, I., Del Ser, J., Bilbao, M.N., and Kasabov, N., Evolving spiking Neural Networks for online learning over drifting data streams, Neural Networks, 2018, vol. 108, pp. 1–19. https://doi.org/10.1016/j.neunet.2018.07.014
Bakhshiev, A., Demcheva, A., and Stankevich, L., CSNM: The compartmental spiking neuron model for developing neuromorphic information processing systems, Stud. Comput. Intell., 2022, vol. 1008 SCI, pp. 327–333. https://doi.org/10.1007/978-3-030-91581-0_43
Korsakov, A., Astapova, L., and Bakhshiev, A., The method of structural adaptation of the compartmental spiking neuron model, Lect. Notes Networks Syst., 2023, vol. 460 LNNS, pp. 545–553. https://doi.org/10.1007/978-3-031-20875-1_51
Eremenko, E.A., Korsakov, A.M., and Bakhshiev, A.V., The incremental learning algorithm for compartmental spiking neuron model, J. Phys.: Conf. Ser., 2022, vol. 2388, no. 1, p. 012036. https://doi.org/10.1088/1742-6596/2388/1/012036
UCI Machine Learning Repository: Iris Data Set. https://archive.ics.uci.edu/ml/datasets/iris. Accesses March 15, 2023.
Funding
The work was supported by the state task of the Russian Ministry of Education and Science for 2023 “Research and development of a biosimilar system for controlling the behavior of mobile robots based on energy-efficient soft-ware and hardware neuromorphic tools” (FNRG-2022-0016 1021060307690-3-1.2.1;2.2.2).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
About this article
Cite this article
Korsakov, A.M., Isakov, T.T. & Bakhshiev, A.V. Strategy of Incremental Learning on a Compartmental Spiking Neuron Model. Opt. Mem. Neural Networks 32 (Suppl 2), S237–S243 (2023). https://doi.org/10.3103/S1060992X23060073
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1060992X23060073