Abstract
In this paper, the global Mittag-Leffler stability of fractional Hopfield neural networks (FHNNs) with \(\delta \)-inverse hölder neuron activation functions are considered. By applying the Brouwer topological degree theory and inequality analysis techniques, the proof of the existence and uniqueness of equilibrium point is addressed. By constructing the Lure’s Postnikov-type Lyapunov functions, the global Mittag-Leffler stability conditions are achieved in terms of linear matrix inequalities (LMIs). Finally, three numerical examples are given to verify the validity of the theoretical results.
Similar content being viewed by others
REFERENCES
Hopfield, J.J., Neural networks and physical systems with emergent collective computational abilities Proc. Natl. Acad. Sci., 1982, vol. 79, no. 8, pp. 2554–2558.
Podlubny, I., Fractional Differential Equations, San Diego, CA: Academic Press, 1999.
Banerjee, S. and Verghese, G., Nonlinear Phenomena in Power Electronics: Bifurcation, Chaos, Control, and Applications, New York: Wiley-IEEE Press, 2001.
Liberzon, D., Switching in System and Control, Birkhäuser Boston, 2001.
Gupta, M., Jin, L., and Homma, N., Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory, New York: Wiley Interscience, 2003.
Qin, S. and Xue, X., A two-layer recurrent neural network for nonsmooth convex optimization problems, IEEE Trans. Neural Networks Learn., 2015, vol. 26, no. 6, pp. 1149–1160.
Li, Y., Chen, Y., and Podlubny, I., Stability of fractional-order nonlinear dynamic systems: Lyapunov direct method and generalized Mittag-Leffler stability, Comput. Math. Appl., 2010, vol. 59, pp. 1810–1821.
Liu, M. and Wu, H., Stochastic finite-time synchronization for discontinuous semi-Markovian switching neural networks with time delays and noise disturbance, Neurocomputing, 2018, vol. 310, no. 6, pp. 246–264.
Wu, H., Zhang, X., and Xue, S., LMI conditions to global Mittag-Leffler stability of fractional-order neural networks with impulses, Neurocomputing, 2016, vol. 193, pp. 148–154.
Wu, G.C., Baleanu, D., and Luo, W.H., Lyapunov functions for Riemann-Liouville-like fractional difference equation, Appl. Math. Comput., 2017, vol. 314, pp. 228–236.
Wu, H., Tao, F., Qin, L., Shi, R., and He, L., Robust exponential stability for interval neural networks with delays and non-Lipschitz activation functions, Nonlinear Dyn., 2011, vol. 66, no. 4, pp. 479–487.
Picozzi, S. and West, B.J., Fractional Langevin model of memory in financial markets, Phys. Rev. E, 2016, vol. 66, no. 4, 046118.
Reyes-Melo, E., Martinez-Vega, J., Guerrero-Salazar, C., and Ortiz-Mendez, U., Application of fractional calculus to the modeling of dielectric relaxation phenomena in polymeric materials, J. Appl. Polym. Sci., 2005, vol. 98, no 2. pp 923–935.
Özalp, N. and Demi̇rci̇, E., A fractional order SEIR model with vertical transmission, Math. Comput. Modell., 2011, vol. 54, nos. 1–2, pp. 1–6.
Soczkiewicz, E., Application of fractional calculus in the theory of viscoelasticity, Mol. Quantum Acoust., 2002, vol. 23, pp. 397–404.
Hilfer, R., Applications of Fractional Calculus in Physics, World Scientific, 2000.
Arena, P., Caponetto, R., Fortuna, L., and Porto, D., Bifurcation and chaos in noninteger order cellular neural networks, Int. J. Bifurcation Chaos, 1998, vol. 8, no. 7, pp. 1527–1539.
Stamova, I., Stamov, G., Simeonov, S., and Ivanov, A., Mittag-Leffler stability of impulsive fractional-order bidirectional associative memory neural networks with time-varying delays, Trans. Inst. Meas. Control, 2018, vol. 40, no. 10, pp. 3068–3077.
Chen, J., Li, C., and Yang, X., Asymptotic stability of delayed fractional-order fuzzy neural networks with impulse effects, J. Franklin Inst., 2018, vol. 355, no. 15, pp. 7595–7608.
Peng, L., Zeng, Z., and Wang, J., Multiple Mittag-Leffler stability of fractional-order recurrent neural networks, IEEE Trans. Syst. Man Cybern. Syst., 2015, vol. 99, pp. 1–10.
Wan, L. and Wu, A., Multiple Mittag-Leffler stability and locally asymptotical ω-periodicity for fractional-order neural networks, Neurocomputing, 2018, vol. 315, pp. 272–282.
Wan, L. and Wu, A., Multistability in Mittag-Leffler sense of fractional-order neural networks with piecewise constant arguments, Neurocomputing, 2018, vol. 286, pp. 1–10.
Liu, P., Nie, X., and Liang, J., Multiple Mittag-Leffler stability of fractional-order competitive neural networks with Gaussian activation functions, Neural Networks, 2018, vol. 108, pp. 452–465.
Wang, L., Wu, H., Liu, D., Boutat, D., and Chen, Y., Lur’e Postnikov Lyapunov functional technique to global Mittag-Leffler stability of fractional-order neural networks with piecewise constant argument, Neurocomputing, 2018, vol. 302, pp. 23–32.
Bao, H., Cao, J., and Kurths, J., State estimation of fractional-order delayed memristive neural networks, Nonlinear Dyn., 2018, vol. 94, no. 2, pp. 1215–1225.
Bao, H., Park, J.H., and Cao, J., Synchronization of fractional-order complex-valued neural networks with time delay, Neural Networks, 2016, vol. 81, pp. 16–28.
Bao, H., Park, J.H., and Cao, J., Synchronization of fractional-order delayed neural networks with hybrid coupling, Complexity, 2016, vol. 21, pp. 106–112.
Yang, X., Li, C., and Song, Q., Global Mittag-Leffler stability and synchronization analysis of fractional-order quaternion-valued neural networks with linear threshold neurons, Neural Networks, 2018, vol. 105, pp. 88–103.
Zhao, W. and Wu, H., Fixed-time synchronization of semi-Markovian jumping neural networks with time-varying delays, Adv. Diff. Equations, 2018. https://doi.org/10.1186/s13662-018-1666-z
Peng, X., Wu, H., and Cao, J., Global nonfragile synchronization in finite time for fractional-order discontinuous neural networks with nonlinear growth activations, IEEE Trans. Neural Networks Learn. Syst., 2019, vol. 30, no. 7, pp. 2123–2137. https://doi.org/10.1109/TNNLS.2018.2876726
Peng, X., Wu, H., Song, K., and Shi, J., Global synchronization in finite time for fractional-order neural networks with discontinuous activations and time delays, Neural Networks, 2017, vol. 94, pp. 46–54.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors declare that they have no conflict of interest.
About this article
Cite this article
Xiaohong Wang, Huaiqin Wu Global Mittag-Leffler Stability of Fractional Hopfield Neural Networks with δ-Inverse Hölder Neuron Activations. Opt. Mem. Neural Networks 28, 239–251 (2019). https://doi.org/10.3103/S1060992X19040064
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1060992X19040064