﻿ 基于Gronwall积分不等式的Hopfield神经网络稳定性的新判据 A New Criterion for Stability of Hopfield Neural Network Based on Gronwall Integral Inequality

Vol. 07  No. 12 ( 2018 ), Article ID: 28302 , 9 pages
10.12677/AAM.2018.712194

A New Criterion for Stability of Hopfield Neural Network Based on Gronwall Integral Inequality

Xingshou Huang, Ricai Luo, Wusheng Wang

School of Mathematics and Statistics, Hechi University, Yizhou Guangxi

Received: Dec. 2nd, 2018; accepted: Dec. 22nd, 2018; published: Dec. 29th, 2018

ABSTRACT

When people study Hopfield time-delay neural network, Lyapunov function is usually used to analyze the stability of the system. But, in this paper, we study the stability of Hopfield neural network by using Gronwall integral inequalities, and obtain the new criterion of global exponential stability of Hopfield neural network and its delay system. Finally, we demonstrate the validity of the results by a numerical example.

Keywords:Gronwall Integral Inequalities, Hopfield Neural Networks, Time Delays, Exponential Stability

1. 引言

Gronwall不等式在微分方程定性理论研究中也发挥极其重要的作用，并且得到不断的推广和广泛应用 [23] - [38] ，但是用于研究神经网络系统的稳定性比较少见。

$\stackrel{˙}{x}\left(t\right)=-Ax\left(t\right)+Bg\left(x\left(t\right)\right)+Cg\left(x\left(t-\tau \right)\right)+I$ (1)

$‖M‖=\sqrt{{\lambda }_{\mathrm{max}}\left({A}^{\text{T}}A\right)}$ ，其中， ${\lambda }_{\mathrm{max}}\left({A}^{\text{T}}A\right)$ 表示 ${A}^{\text{T}}A$ 的最大特征值， $‖x‖=\sqrt{{x}_{1}^{2}+{x}_{2}^{2}+\cdots +{x}_{n}^{2}}$

$\stackrel{˙}{y}\left(t\right)=-Ay\left(t\right)+Bf\left(y\left(t\right)\right)+Cf\left(y\left(t-\tau \right)\right)$ , (2)

$u\left(t\right)\le K+{\int }_{\alpha }^{t}u\left(s\right)g\left(s\right)\text{d}s,\text{\hspace{0.17em}}\alpha \le t\le \beta$

$u\left(t\right)\le K\cdot \mathrm{exp}\left[{\int }_{\alpha }^{t}g\left(s\right)\text{d}s\right],\text{\hspace{0.17em}}\alpha \le t\le \beta$ .

2. 稳定性分析

2.1. 无时滞的情形分析

$\stackrel{˙}{y}\left(t\right)=-Ay\left(t\right)+Bf\left(y\left(t\right)\right)$ (3)

$\stackrel{˙}{y}\left(t\right)=-Ay\left(t\right)$ (4)

$\mathrm{exp}\left[-At\right]=\left[\begin{array}{cccc}{\text{e}}^{-{a}_{1}t}& & & 0\\ & {\text{e}}^{-{a}_{2}t}& & \\ & & \ddots & \\ 0& & & {\text{e}}^{-{a}_{n}t}\end{array}\right]$ ,

I) $M=\sqrt{n}\cdot \mathrm{max}\left\{|{\eta }_{1}|,|{\eta }_{2}|,\cdots ,|{\eta }_{n}|\right\}$ ，显然，M > 0。

II) $\sigma =\mathrm{min}\left\{{a}_{1},{a}_{2},\cdots ,{a}_{n}\right\}$

$y\left(t\right)=Y\left(t\right)+{\int }_{0}^{t}{e}^{-A\left(t-s\right)}Bf\left(y\left(s\right)\right)\text{d}s$ ，实际上，这里 $Y\left(t\right)={e}^{-At}\eta$ ，两边取范数

$\begin{array}{c}‖y\left(t\right)‖=‖Y\left(t\right)‖+{\int }_{0}^{t}‖{e}^{-A\left(t-s\right)}Bf\left(y\left(s\right)\right)‖\text{d}s\\ \le M{\text{e}}^{-\sigma t}+{\int }_{0}^{t}‖{e}^{-A\left(t-s\right)}‖‖B‖‖f\left(y\left(s\right)\right)‖\text{d}s\\ \le M{\text{e}}^{-\sigma t}+L‖B‖{\int }_{0}^{t}{\text{e}}^{-\sigma \left(t-s\right)}‖y\left(s\right)‖\text{d}s\end{array}$

${\text{e}}^{\sigma t}‖y\left(t\right)‖\le M+L‖B‖{\int }_{0}^{t}{\text{e}}^{\sigma s}‖y\left(s\right)‖\text{d}s$

${\text{e}}^{\sigma t}‖y\left(t\right)‖\le M{\text{e}}^{L‖B‖{\int }_{0}^{t}\text{d}s}=M{\text{e}}^{L‖B‖t}$

2.2. 具有时滞的情况分析

$D\left(y\right)=\left[\begin{array}{cccc}{f}_{1}\left({y}_{1}\right)/{y}_{1}& & & 0\\ & {f}_{2}\left({y}_{2}\right)/{y}_{2}& & \\ & & \ddots & \\ 0& & & {f}_{n}\left({y}_{n}\right)/{y}_{n}\end{array}\right]$ (5)

$\stackrel{˙}{y}\left(t\right)=\left(-A+BD\left(y\right)\right)y\left(t\right)$ (6)

$‖\phi \left(t\right)‖\le ‖\eta ‖{\text{e}}^{-{\sigma }_{1}t}$ (7)

$\stackrel{˙}{y}\left(t\right)=\left(-A+BD\left(y\right)\right)y\left(t\right)+Cf\left(y\left(t-\tau \right)\right)$ (8)

$t=0$ 时，对应初值为 $\eta =\left({\eta }_{1},{\eta }_{2},\cdots ,{\eta }_{n}\right)$ ，方程(8)的解可以表示为

$y\left(t\right)=\phi \left(t\right)+{\int }_{0}^{t}{e}^{\left(L‖B‖E-A\right)\left(t-s\right)}Cf\left(y\left(s-\tau \right)\right)\text{d}s$

$\begin{array}{c}‖y\left(t\right)‖\le ‖\phi \left(t\right)‖+{\int }_{0}^{t}‖{e}^{\left(L‖B‖E-A\right)\left(t-s\right)}Cf\left(y\left(s-\tau \right)\right)‖\text{d}s\\ \le ‖\phi \left(t\right)‖+{\int }_{0}^{t}‖{e}^{\left(L‖B‖E-A\right)\left(t-s\right)}‖‖C‖‖f\left(y\left(s-\tau \right)\right)‖\text{d}s\\ \le ‖\eta ‖{\text{e}}^{-{\sigma }_{1}t}+{\int }_{-\tau }^{t-\tau }{\text{e}}^{\left(L‖B‖-\sigma \right)\left(t-\tau -s\right)}‖C‖L‖y\left(s\right)‖\text{d}s\\ =‖\eta ‖{\text{e}}^{-{\sigma }_{1}t}+{\text{e}}^{{\sigma }_{1}t}‖C‖L{\int }_{-\tau }^{t-\tau }{\text{e}}^{-{\sigma }_{1}\left(t-s\right)}‖y\left(s\right)‖\text{d}s\end{array}$

$\begin{array}{c}{\text{e}}^{{\sigma }_{1}t}‖y\left(t\right)‖=‖\eta ‖+{\text{e}}^{{\sigma }_{1}t}‖C‖L{\int }_{-\tau }^{t-\tau }{\text{e}}^{{\sigma }_{1}t}{\text{e}}^{-{\sigma }_{1}\left(t-s\right)}‖y\left(s\right)‖\text{d}s\\ =‖\eta ‖+{\text{e}}^{{\sigma }_{1}t}‖C‖L{\int }_{-\tau }^{t-\tau }{\text{e}}^{{\sigma }_{1}s}‖y\left(s\right)‖\text{d}s\end{array}$

${\text{e}}^{{\sigma }_{1}t}‖y\left(t\right)‖\le ‖\eta ‖{\text{e}}^{{\text{e}}^{{\sigma }_{1}\tau }‖C‖L{\int }_{-\tau }^{t-\tau }\text{d}s}=‖\eta ‖{\text{e}}^{{\text{e}}^{{\sigma }_{1}\tau }‖C‖Lt}$

3. 数值仿真

$\left(\begin{array}{c}\stackrel{˙}{x}\left(t\right)\\ \stackrel{˙}{y}\left(t\right)\end{array}\right)=-A\left(\begin{array}{c}x\left(t\right)\\ y\left(t\right)\end{array}\right)+B\left(\begin{array}{c}{f}_{1}\left(x\left(t\right)\right)\\ {f}_{2}\left(y\left(t\right)\right)\end{array}\right)$ (9)

Figure 1. The state rail diagram of system (9) ( $L‖B‖-\sigma <0$ )

$\left(\begin{array}{c}\stackrel{˙}{x}\left(t\right)\\ \stackrel{˙}{y}\left(t\right)\end{array}\right)=-A\left(\begin{array}{c}x\left(t\right)\\ y\left(t\right)\end{array}\right)+B\left(\begin{array}{c}{f}_{1}\left(x\left(t\right)\right)\\ {f}_{2}\left(y\left(t\right)\right)\end{array}\right)+C\left(\begin{array}{c}{f}_{1}\left(x\left(t-\tau \right)\right)\\ {f}_{2}\left(y\left(t-\tau \right)\right)\end{array}\right)$ (10)

Figure 2. The state rail diagram of system (9) ( $L‖B‖-\sigma >0$ )

Figure 3. The state rail diagram of system (10) ( ${\text{e}}^{{\sigma }_{1}\tau }‖C‖L-{\sigma }_{1}<0$ )

Figure 4. The state rail diagram of system (10) ( ${\text{e}}^{{\sigma }_{1}\tau }‖C‖L-{\sigma }_{1}>0$ )

A New Criterion for Stability of Hopfield Neural Network Based on Gronwall Integral Inequality[J]. 应用数学进展, 2018, 07(12): 1658-1666. https://doi.org/10.12677/AAM.2018.712194

1. 1. Hopfield, J.J. (1984) Neurons with Graded Response Have Collective Computational Properties Like Those of Two-State Neurons. Proceedings of the National Academy of Sciences of the USA, 81, 3088-3092. https://doi.org/10.1073/pnas.81.10.3088

2. 2. Abe, S., Kawakami, J. and Hirasawa, K. (1992) Solving Inequality Constrained Combinatorial Optimization Problems by the Hopfield Neural Networks. Neural Networks, 5, 663-670. https://doi.org/10.1016/S0893-6080(05)80043-7

3. 3. Tamura, H., Zhang, Z., Xu, X.S., Ishii, M. and Tang, Z. (2005) Lagrangian Object Relaxation Neural Network for Combinatorial Optimization Problems. Neurocomputing, 68, 297-305. https://doi.org/10.1016/j.neucom.2005.03.003

4. 4. Wang, R.L., Tang, Z. and Cao, Q.P. (2002) A Learning Method in Hopfield Neural Network for Combinatorial Optimization Problem. Neurocomputing, 48, 1021-1024. https://doi.org/10.1016/S0925-2312(02)00596-9

5. 5. Rout, S., Seethalakshmy, Srivastava, P. and Majumdar, J. (1998) Multi-Modal Image Segmentation Using a Modified Hopfield Neural Network Original Research Article. Pattern Recognition, 31, 743-750. https://doi.org/10.1016/S0031-3203(97)00089-7

6. 6. Sammouda, R., Adgaba, N., Touir, A. and Al-Ghamdi, A. (2014) Agriculture Satellite Image Segmentation Using a Modified Artificial Hopfield Neural Network Original Research Article. Computers in Human Behavior, 30, 436-441. https://doi.org/10.1016/j.chb.2013.06.025

7. 7. Suganthan, P., Teoh, E. and Mital, D. (1995) Pattern Recognition by Homomorphic Graph Matching Using Hopfield Neural Networks Original Research Article. Image and Vision Computing, 13, 45-60. https://doi.org/10.1016/0262-8856(95)91467-R

8. 8. Laskaris, N., Fotopoulos, S., Papathanasopoulos, P. and Bezerianos, A. (1997) Robust Moving Averages, with Hopfield Neural Network Implementation, for Monitoring Evoked Potential Signals Original Research Article. Electroencephalography and Clinical Neurophysiology/Evoked Potentials Section, 104, 151-156.

9. 9. Calabuig, D., Monserrat, J.F., Gmez-Barquero, D. and Lzaro, O. (2008) An Efficient Dynamic Resource Allocation Algorithm for Packet-Switched Communication Networks Based on Hopfield Neural Excitation Method Original Research Article. Neurocomputing, 71, 3439-3446. https://doi.org/10.1016/j.neucom.2007.10.009

10. 10. Marcus, C. and Westervelt, R. (1989) Stability of Analog Neural Networks with Delay. Physical Review A, 39, 347-359. https://doi.org/10.1103/PhysRevA.39.347

11. 11. Wu, J. (1999) Symmetric Functional-Differential Equations and Neural Networks with Memory. Transactions of the American Mathematical Society, 350, 4799-4838. https://doi.org/10.1090/S0002-9947-98-02083-2

12. 12. Wu, J. and Zou, X. (1995) Patterns of Sustained Oscillations in Neural Networks with Time Delayed Interactions. Applied Mathematics and Computation, 73, 55-75.

13. 13. Gopalsamy, K. and He, X. (1994) Stability in Asymmetric Hopfield Nets with Transmission Delays. Physica D, 76, 344-358. https://doi.org/10.1016/0167-2789(94)90043-4

14. 14. Zhang, W.N. (2006) A Weak Condition of Globally Asymptotic Stability for Neural Networks. Applied Mathematics Letters, 19, 1210-1215. https://doi.org/10.1016/j.aml.2006.01.009

15. 15. Orman, Z. (2012) New Sufficient Conditions for Global Stability of Neutral-Type Neural Networks with Time Delays. Neurocomputing, 97, 141-148. https://doi.org/10.1016/j.neucom.2012.05.016

16. 16. Zhang, F. (2005) The Schur Complement and Its Applications. Numerical Methods and Algorithms, Vol. 4, Springer-Verlag, New York, 34.

17. 17. Chen, Y. and Xu, H. (2012) Expo-nential Stability Analysis and Impulsive Tracking Control of Uncertain Time-Delayed Systems. Journal of Global Opti-mization, 52, 323-334. https://doi.org/10.1007/s10898-011-9669-2

18. 18. Xu, H., Chen, Y. and Teo, K.L. (2010) Global Exponential Stability of Impulsive Discrete-Time Neural Networks with Time-Varying Delays. Applied Math-ematics and Computations, 217, 537-544. https://doi.org/10.1016/j.amc.2010.05.087

19. 19. Forti, M. (1994) On Global Asymptotic Stability of a Class of Nonlinear Systems Arising in Neural Network Theory. Journal of Differential Equations, 113, 246-264. https://doi.org/10.1006/jdeq.1994.1123

20. 20. Forti, M., Maneti, S. and Marini, M. (1994) Necessary and Sufficient Conditions for Absolute Stability of Neural Networks. IEEE Transactions on Circuits and Systems I, 41, 491-494. https://doi.org/10.1109/81.298364

21. 21. Forti, M. and Tesi, A. (1995) New Conditions for Global Stability of Neural Networks with Application to Linear and Quadratic Programming Problems. IEEE Transactions on Circuits and Systems I, 42, 354-366. https://doi.org/10.1109/81.401145

22. 22. Gasull, A., Llibre, J. and Sotomayor, J. (1991) Global Asymptotic Stability of Differential Equations in the Plane. Journal of Differential Equations, 91, 327-336. https://doi.org/10.1016/0022-0396(91)90143-W

23. 23. Gronwall, T.H. (1919) Note on the Derivatives with Respect to a Parameter of the Solutions of a System of Differential Equations. Annals of Mathematics, 20, 292-296. https://doi.org/10.2307/1967124

24. 24. Bellman, R. (1943) The Stability of Solutions of Linear Differential Equations. Duke Mathematical Journal, 10, 643-647. https://doi.org/10.1215/S0012-7094-43-01059-2

25. 25. Abdeldaim, A. (2016) Nonlinear Retarded Integral Inequalities of Type and Applications. Journal of Mathematical Inequalities, 10, 285-299.

26. 26. Lipovan, O. (2000) A Retarded Gronwall-Like Inequality and Its Applications. Journal of Mathematical Analysis and Applications, 252, 389-401. https://doi.org/10.1006/jmaa.2000.7085

27. 27. Agarwal, R.P., Deng, S. and Zhang, W. (2005) Generalization of a Retarded Gronwall-Like Inequality and Its Applications. Applied Mathematics and Computation, 165, 599-612. https://doi.org/10.1016/j.amc.2004.04.067

28. 28. Cheung, W.S. (2006) Some New Nonlinear Inequalities and Applications to Boundary Value Problems. Nonlinear Analysis, 64, 2112-2128. https://doi.org/10.1016/j.na.2005.08.009

29. 29. Abdeldaim, A. and Yakout, M. (2011) On Some New Integral Ine-qualities of Gronwall-Bellman-Pachpatte Type. Applied Mathematics and Computation, 217, 7887-7899. https://doi.org/10.1016/j.amc.2011.02.093

30. 30. El-Owaidy, H., Ragab, A.A., Abuelela, W. and El-Deeb, A.A. (2014) On Some New Nonlinear Integral Inequalities of Gronwall-Bellman Type. Kyungpook Mathematical Journal, 54, 555-575. https://doi.org/10.5666/KMJ.2014.54.4.555

31. 31. Sano, H. and Kunimatsu, N. (1994) Modified Gronwall’s Inequality and Its Application to Stabilization Problem for Semilinear Parabolic Systems. Systems & Control Letters, 22, 145-156. https://doi.org/10.1016/0167-6911(94)90109-0

32. 32. Ye, H.P., Gao, J.M. and Ding, Y.S. (2007) A Generalized Gronwall Inequality and Its Application to a Fractional Differential Equation. Journal of Math-ematical Analysis and Applications, 328, 1075-1081. https://doi.org/10.1016/j.jmaa.2006.05.061

33. 33. Medved, M. (2002) Integral Inequalities and Global Solutions of Semilinear Evolution Equations. Journal of Mathematical Analysis and Applications, 267, 643-650. https://doi.org/10.1006/jmaa.2001.7798

34. 34. Ma, Q.H. and Pecaric, J. (2008) Some New Explicit Bounds for Weakly Singular Integral Inequalities with Applications to Fractional Differential and Integral Equations. Journal of Mathematical Analysis and Applications, 341, 894-905. https://doi.org/10.1016/j.jmaa.2007.10.036

35. 35. Deng, S. and Prather, C. (2008) Generalization of an Impulsive Nonlinear Singular Gronwall-Bihari Inequality with Delay. Journal of Inequalities in Pure and Applied Mathematics, 9, Article 34.

36. 36. Mazouzi, S. and Tatar, N. (2010) New Bounds for Solutions of a Singular Integro-Differential Inequality. Mathematical Inequalities & Applications, 13, 427-435.

37. 37. Wang, H. and Zheng, K. (2010) Some Nonlinear Weakly Singular Integral Inequalities with Two Vari-ables and Applications. Journal of Inequalities and Applications, 2010, Article ID: 345701.

38. 38. Cheng, K., Guo, C. and Tang, M. (2014) Some Nonlinear Gronwall-Bellman-Gamidov Integral Inequalities and Their Weakly Singular Analogues with Applications. Abstract and Applied Analysis, 2014, Article ID: 562691.