Abstract
The new network model with gauss nonlinear self-feedback is constructed. The appropriate initial value of each parameter is selected, making the network reflect the chaotic dynamic characteristics. The comparison of simulation figures illustrates the feasibility of the application of the model, and the network’s sensitivity to chaotic parameters is also reflected. It is proved that the width coefficient increase or decrease in different structure-function influences the output to change differently by comparing Gaussian and the contrary multiquadric function. The new model is used in the combinatorial optimization problem. The experimental data show that the new network can effectively escape from the minimum range of chaotic characteristics and achieve a high convergence effect to a stationary point if appropriate parameters are adopted. We also study the influence of the ability of optimization belonging to main parameters in the network.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Xu, Y.Q., He, S.P.: Self-feedback chaotic neural networks with trigonometric functions and its applications. In: Proceedings of the 2009 China Conference on Control and Decision Making, Guilin, Guangxi (2009)
Xu, Y.Q., Yang, X.L.: Chaotic neural network with anti-trigonometric function self-feedback and its application. J. Harbin Univ. Commer. (Nat. Sci. Edn.) 26(3), 324–328 (2010)
Tong, X., Li, J.B.: Robust encryption face recognition algorithm based on composite chaos in cloud environment. Mod. Electron. Technol. 42(06), 166–169 (2019)
Chen, L., Aihara, K.: Chaotic simulated annealing by a neural network model with transient chaos. Neural Netw. 8(6), 915–930 (1995)
Xu, Y., Yu, Q.: Optimizing logistic distribution routing problem based on wavelet chaotic neural network. In: Proceedings of the 2017 Chinese Control and Decision Conference, CCDC, pp. 3460–3464 (2017)
Hopfield, J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79, 2554–2558 (1982)
Wang, X.-Y., Bao, X.-M.: A novel image block cryptosystem based on a spatiotemporal chaotic system and a chaotic neural network. Chin. Phys. B 22(5), 050508 (2013)
Abdoun, N., El Assad, S., Hoang, T.M., Deforges, O., Assaf, R., Khalil, M.: Designing two secure keyed hash functions based on sponge construction and the chaotic neural network. Entropy 22(9), 1012 (2020)
Ye, Y.G., Xu, Y.Q.: SLF chaotic neural network and its application. Comput. Eng. Appl. (2015)
Xiu, C.B., Liu, C., Guo, F.H., Cheng, Y., Luo, J.: Research on control strategy and application of delayed chaotic neuron/network. ActaPhys. Sin. (2015)
Hu, Z.Q., Li, W.J., Qiao, J.F.: Frequency conversion sinusoidal chaotic neural network based on adaptive simulated annealing. J. Electron. 47(3), 613–622 (2019)
Hu, N.W., Qi, M.L.: Molecular dynamics simulation of displacement cascades in Ni-Mo alloy. Nucl. Sci. Tech. 26(6), 060603 (2015)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, N., Zhou, B., Wang, Y. (2022). Gauss Nonlinear Self-feedback Chaotic Neural Network and Its Application. In: Hassanien, A.E., Xu, Y., Zhao, Z., Mohammed, S., Fan, Z. (eds) Business Intelligence and Information Technology. BIIT 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 107. Springer, Cham. https://doi.org/10.1007/978-3-030-92632-8_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-92632-8_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92631-1
Online ISBN: 978-3-030-92632-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)