Use of Izhikevich neurons in Hopfield models
DOI:
https://doi.org/10.17721/1812-5409.2025/1.16Keywords:
Izhikevich neuron, Hopfield network, chaotic activation functions, neural networks, self-concept of the individual, dichotomous orientation of the transformation of the self-concept of the individual, constructive transformation of the self-concept of the individual, destructive transformation of the self-concept of the individualAbstract
The Izhikevich chaotic neuron model represents a considerable advancement in computational neuroscience by offering a mathematical framework that closely mirrors the behavior of biological neurons, especially in generating chaotic or complex spiking patterns seen in the brain. This model has garnered attention due to its ability to replicate a wide range of real-life neural dynamics, including bursting and tonic spiking, which are fundamental to understanding the complexities of neural communication and processing. On the other hand, Hopfield networks, a type of recurrent neural network, have long been recognized for their ability to serve as content- addressable memory systems, storing and recalling information based on associative dynamics. Often described as spin glass systems, Hopfield networks operate by finding stable states or patterns within the neural network, emulating certain memory functions of the human brain. Recently, research into innovative activation functions has opened new possibilities for enhancing the capabilities of recurrent networks. The chaotic activation functions, in particular, present an intriguing area of exploration within Hopfield networks. This article investigates the effects of embedding these chaotic activation functions in Hopfield networks, examining how they influence the network's stability, adaptability, and efficiency. Through this exploration, we aim to reveal the impact of chaos on the network's dynamics, providing insights that could potentially lead to improved performance in applications requiring complex memory and associative processing. The study contributes to the growing field of neuromorphic engineering, with implications for both artificial intelligence and neuroscience.
Pages of the article in the issue: 122 - 129
Language of the article: English
References
Babloyantz, A., Nicolis, S., & Salazor, M. (1985). Evidence of chaotic dynamics of brain activity during the sleep cycle. Physics Letters A., 111, 152–156. https://doi.org/10.1016/0375-9601(85)90444-X
Boroday, N., Chekhun, V., Golubeva, E., & Klyushin, D. (2016). In vitro and in vivo densitometric analysis of DNA content and chromatin texture in tumor cell nuclei under the influence of a nano composite and magnetic field. Advances in Cancer Research & Treatment, 1–11. https://doi.org/10.5171/2016.706183
Chen, X., & Wang, Y. (2023). A Chaotic Neuron and its Ability to Prevent Overfitting. Frontiers in Computing and Intelligent Systems, 5, 53–61. https://doi.org/10.54097/fcis.v5i1.11673
Cursino, C., & Dias, L. (2024). Hybrid Hopfield Neural Network. SN Computer Science, 5, 25–74. https://doi.org/10.1007/s42979-023-02575-6
Deng, Q., Wong, C., & Lin, H. (2024а). Chaotic dynamical system of Hopfield neural network influenced by neuron activation threshold and its image encryption. Nonlinear Dynamics, 112, 1–18. https://doi.org/10.1007/s11071-024-09384-3
Deng, Q., Wong, C., & Lin, H. (2024b). Memristive Hopfield neural network dynamics with heterogeneous activation functions and its application. Chaos Solitons & Fractals, 178, 101–124. https://doi.org/10.1016/j.chaos.2023.114387
Dubey, S. R., Singh, S. K., & Chaudhuri B. B. (2022). Activation Functions in Deep Learning: A comprehensive Survey and Benchmark. Neurocomputing, 503, 24–27. https://doi.org/10.1016/j.neucom.2022.06.111
Freeman, W. (1987). Simulation of Chaotic EEG Patterns with a Dynamic Model of the Olfactory System. Biological Cybernetics, 56, 139–150. https://doi.org/10.1007/BF00317988
Hirsch, M. (1989). Convergent Activation Dynamics in Continuous Time Neural Networks. Neural Networks, 2, 331–351. https://doi.org/10.1016/0893-6080(89)90018-X
Hopfield, J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci U S A., 79 (Apr), 2554–2558. https://doi.org/10.1073/pnas.79.8.2554
Kashyap, D., Dsouza, N., Shi, L., & Beymer, D. (2022). Hopfield Encoding Networks. https://doi.org/10.13140/RG.2.2.17209.65123
Kilicarslan, S., Adem, K., & Celik M. (2021). An overview of the activation functions used in deep learning algorithms. Journal of New Results in Science, 10, 75–88. https://doi.org/10.54187/jnrs.1011739
Klyushin, D., Golubeva, K., Boroday, N., & Shervarly, D. (2021). Breast Cancer Diagnosis Using Machine Learning and Fractal Analysis of Malignancy-Associated Changes in Buccal Epithelium. Artificial Intelligence, Machine Learning, and Data Science Technologies Future Impact and Well- Being for Society, 5, 1–18. https://doi.org/10.1201/9781003153405-1
Krotov, D. (2023). A new frontier for Hopfield networks. Nature Reviews Physics, 5, 52–70. https://doi.org/10.1038/s42254-023-00595-y
Liang, X., Yang, Y., Wang, R., & Chen, J. (2024). Synchronization of delayed stochastic reaction-diffusion Hopfield neural networks via sliding mode control. Nonlinear Analysis Modelling and Control, 29, 1–19. https://doi.org/10.15388/namc.2024.29.34884
Lieberman-Aiden, E. (2009). Comprehensive mapping of long-range interactions reveals folding principles of the human Genome. Science, 326, 289–193. https://doi.org/10.1126/science.1181369
Magallon, D., Garcia, J., Huerta, G., & Jaimes, R. (2024). Real-time neural identification using a recurrent wavelet first-order neural network of a chaotic system implemented in an FPAA. Integration, 96, 384–393. https://doi.org/10.1016/j.vlsi.2023.102134
Nieburgs, H. (1968). Recent progress in the interpretation of malignancy associated changes (MAC). Acta Cytologica, 12, 445–453. https://doi.org/10.1155/238921
Ogden, G., Cowpe, J., & Green, M. (1990). The effect of distant malignancy upon quantitative cytologic assessment of normal oral mucosa. Cancer, 65, 477–480. https://doi.org/10.1002/1097-0142(19900201)65:3<477::AID-CNCR2820650317>3.0.CO;2-G
Radak, M., Lafta, H., & Fallahi, H. (2023). Machine learning and deep learning techniques for breast cancer diagnosis and classification: a comprehensive review of medical imaging studies. Journal of Cancer Research and Clinical Oncology, 49, 10473–10491. https://doi.org/10.1007/s00432-023-04956-z
Shepherd, G. (1990). The synaptic organization of the brain. Oxford University Press. https://doi.org/10.1093/acprof:oso/9780195159561.001.1
Skarda, C., & Freeman, W. (1987). How brains make chaos in order to make sense of the world. Behavioral and Brain Sciences, 10, 161–195. https://doi.org/10.1017/S0140525X00047336
Sparrow, C. (1982). The Lorenz Equations. Bifurcations, Chaos, and Strange Attractors. Applied Mathematical Sciences, 41, 26–50. https://doi.org/10.1007/978-1-4612-5767-7
Tsuda, I. (1992). Dynamic link of memory – Chaotic memory map in nonequilibrium neural networks. Neural Networks, 5, 857–893. https://doi.org/10.1016/S0893-6080(05)80029-2
Wang, X., Ren H., & Wang A. (2022). Smish: A Novel Activation Function for Deep Learning Methods. Electronics, 11, 540–545. https://doi.org/10.3390/electronics11040540
Yao, Y., & Freeman, W. (1990). Model of Biological Pattern Recognition with Spatially Chaotic Dynamics. Neural Networks, 3, 153–170. https://doi.org/10.1016/0893-6080(90)90086-Z
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Dmitriy Klyushin, Oleksandr Maistrenko
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
