INFLUENCE OF CHAOS ON ACTIVATION FUNCTIONS IN HOPFIELD NETWORKS

  • O. S. Maistrenko Faculty of Computer Science and Cybernetics, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
  • D. A. Klyushin Faculty of Computer Science and Cybernetics, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Keywords: Hopfield network, activation function, chaotic neural networks, breast cancer

Abstract

Hopfield networks are known for their ability to store and recall patterns. Recently, there has been interest in new types of activation functions and how they can be used in these networks. This paper looks at how chaotic activation functions can be used in Hopfield networks and what effects they have on how the networks work.

References

Dubey S. R., Singh S. K., Chaudhuri B. B. Activation Functions in Deep Learning: A comprehensive Survey and Benchmark. Neurocomputing. 2022. Vol. 503. P. 24–27.

Kilicarslan S., Adem K., Celik M. An overview of the activation functions used in deep learning algorithms. Journal of New Results in Science. 2021. Vol. 10. P.75–88.

Wang X., Ren H., Wang A. Smish: A Novel Activation Function for Deep Learning Methods. Electronics. 2022. Vol. 11. P. 540–545.

Chen X., Wang Y. A Chaotic Neuron and its Ability to Prevent Overfitting. Frontiers in Computing and Intelligent Systems. 2023. Vol. 5. P. 53–61.

Deng Q., Wong C., Lin H. Memristive Hopfield neural network dynamics with heterogeneous activation functions and its application. Chaos Solitons and Fractals. 2024. Vol. 178. P. 101–124.

Deng Q., Wong C., Lin H. Chaotic dynamical system of Hopfield neural network influenced by neuron activation threshold and its image encryption. Nonlinear Dynamics. 2024. Vol. 112. P. 1–18.

Magallon D., Garcia J., Huerta G., Jaimes R. Real-time neural identification using a recurrent wavelet first-order neural network of a chaotic system implemented in an FPAA. Integration. 2024. Vol. 96. P. 384–393.

Krotov D. A new frontier for Hopfield networks. Nature Reviews Physics. 2023. Vol. 5. P. 52–70.

Cursino C., Dias L. Hybrid Hopfield Neural Network. SN Computer Science. 2024. Vol. 5. P. 25–74.

Kashyap S., Dsouza N., Shi L., Beymer D. Hopfield Encoding Networks. 2024.

Liang X., Yang Y., Wang R., Chen J. Synchronization of delayed stochastic reaction-diffusion Hopfield neural networks via sliding mode control. Nonlinear Analysis Modelling and Control. 2024. Vol. 29. P. 1–19.

Lieberman-Aiden E. Comprehensive mapping of long-range interactions revealsfolding principles of the human Genome. Science. 2009. Vol. 326. P. 289–193.

Babloyantz A., Nicolis S., Salazor M. Evidence of chaotic dynamics of brain activity during the sleep cycle. Physics Letters A.1985. Vol. 111. P. 152–156.

Freeman W. Simulation of Chaotic EEG Patterns with a Dynamic Model of the Olfactory System. Biological Cybernetics. 1987. Vol. 56. P. 139–150.

Hirsch M. Convergent Activation Dynamics in Continuous Time Neural Networks. Neural Networks. 1989. Vol. 2. P. 331–351.

Hopfield J. Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA.1982. Vol. 79(Apr). P. 2554–2558.

Shepherd G. The synaptic organization of the brain. Oxford University Press. 1990.

Skarda C., Freeman W. How brains make chaos in order to make sense of the world. Behavioral and Brain Sciences. 1987. Vol. 10. P. 161–195.

Tsuda I. Dynamic link of memory - Chaotic memory map in nonequilibrium neural networks. Neural Networks. 1992. Vol. 5. P. 857–893.

Yao Y., Freeman W. Model of Biological Pattern Recognition with Spatially Chaotic Dynamics. Neural Networks. 1990. Vol. 3. P. 153–170.

Sparrow A. The Lorenz Equations. Bifurcations, Chaos, and Strange Attractors. Applied Mathematical Sciences. 1982. Vol. 41. P. 26–50.

Radak M., Lafta H., Fallahi H. 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. 2023. Vol. 49. P. 10473–10491.

Nieburgs H. Recent progress in the interpretation of malignancy associated changes (MAC). Acta Cytologica. 1968. Vol. 12. P. 445–453.

Boroday N., Chekhun V., Golubeva E., Klyushin D. 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. 2016. Vol. 2016. P. 1–11.

Ogden G., Cowpe J., Green M. The effect of distant malignancy upon quantitative cytologic assessment of normal oral mucosa. Cancer. 1990. Vol. 65. P. 477–480.

Klyushin D., Golubeva K., Boroday N., Shervarly D. 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. 2021. Vol. 5. P. 1–18.

Published
2025-01-14
How to Cite
Maistrenko, O., & Klyushin, D. (2025). INFLUENCE OF CHAOS ON ACTIVATION FUNCTIONS IN HOPFIELD NETWORKS. Journal of Numerical and Applied Mathematics, (2), 36-51. https://doi.org/10.17721/2706-9699.2024.2.02