×
Zhu, Song; Shen, Yi; Chen, Guici

Noise suppress exponential growth for hybrid Hopfield neural networks. (English) Zbl 1486.34082

Math. Comput. Simul. 86, 10-20 (2012).
Summary: In this paper, we show that noise can transform a hybrid neural networks, whose solution may grow exponentially, into a new stochastic one, whose solution grows at most polynomially. In other words, we reveal that noise can suppress the exponential growth in hybrid Hopfield neural networks.

MSC:

34C11 Growth and boundedness of solutions to ordinary differential equations
92B20 Neural networks for/in biological studies, artificial life and related topics
34F05 Ordinary differential equations and systems with randomness
60J20 Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.)

Keywords:

exponential growth; polynomial growth; generalized Itô formula; Markov chain
Cite Review PDF
Full Text: DOI

References:

[1] Appleby, J. A.D.; Mao, X.; Rodkina, A., Stabilization and destabilization of nonlinear differential equations by noise, IEEE Trans. Automat. Contr., 53, 3, 683-691 (2008) · Zbl 1367.93692
[2] Boulanger, C., Stabilization of a class of nonlinear stochastic systems, Nonlinear Anal., 41, 3-4, 277-286 (2000) · Zbl 0962.93088
[3] Cao, J.; Wang, J., Global asymptotic and robust stability of recurrent neural networks with time delays, IEEE Trans. Circ. Syst. I, 52, 2, 417-426 (2005) · Zbl 1374.93285
[4] Deng, F.; Luo, Q.; Mao, X.; Pang, S., Noise suppresses or expresses exponential growth, Syst. Control Lett., 57, 3, 262-270 (2008) · Zbl 1157.93515
[5] Hopfield, J. J., Neural networks and physical systems with emergent collective computational abilities, Proc. Natl. Acad. Sci. U.S.A., 79, 8, 2554-2558 (1982) · Zbl 1369.92007
[6] Hu, G.; Liu, M.; Mao, X.; Song, M., Noise suppresses exponential growth under regime switching, J. Math. Anal. Appl., 355, 2, 783-795 (2009) · Zbl 1173.60024
[7] Hu, L.; Mao, X., Almost sure exponential stabilisation of stochastic systems by state-feedback control, Automatica, 44, 2, 465-471 (2008) · Zbl 1283.93303
[8] Huang, C.; Huang, L.; Yuan, Z., Global stability analysis of a class of delayed cellular neural networks, Math. Comput. Simulat., 70, 3, 133-148 (2005) · Zbl 1094.34052
[9] Huang, H.; Ho, D. W.C.; Qu, Y., Robust stability of stochastic delayed additive neural networks with Markovian switching, Neural Netw., 20, 7, 799-809 (2007) · Zbl 1125.68096
[10] Liang, J.; Cao, J., Global asymptotic stability of bi-directional associative memory networks with distributed delays, Appl. Math. Comput., 152, 2, 415-424 (2005) · Zbl 1046.94020
[11] Liberzon, D., Switching in Systems and Control (2003), Birkhauser: Birkhauser Boston, MA · Zbl 1036.93001
[12] Lou, X.; Cui, B., New LMI conditions for delay-dependent asymptotic stability of delayed Hopfield neural networks, Neurocomputing, 69, 16-18, 2374-2378 (2006)
[13] Mao, X.; Marion, G.; Renshaw, E., Environmental noise suppresses explosion in population dynamics, Stoch. Processes Appl., 97, 1, 95-110 (2002) · Zbl 1058.60046
[14] Mao, X.; Yuan, C., Stochastic Differential Equations with Markovian Switching (2006), Imperial College Press · Zbl 1126.60002
[15] Mao, X.; Yin, G.; Yuan, C., Stabilization and destabilization of hybrid systems of stochastic differential equations, Automatica, 43, 2, 264-273 (2007) · Zbl 1111.93082
[16] Mimkowski, H., Diophantische Approximationen (1907), Teubner: Teubner Leipzig · JFM 38.0220.15
[17] Peng, J.; Xu, Z.; Qiao, H.; Zhang, B., A critical analysis on global convergence of Hopfield-type neural networks, IEEE Trans. Circuits Syst. I, 52, 4, 804-814 (2005) · Zbl 1374.82024
[18] Shen, Y.; Wang, J., Noise-induced stabilization of the recurrent neural networks with mixed time varying delays and Markovian-switching parameters, IEEE Trans. Neural Netw., 18, 6, 1857-1862 (2007)
[19] Song, Q.; Cao, J., Global robust stability of interval neural networks with multiple time-varying delays, Math. Comput. Simulat., 74, 1, 38-46 (2007) · Zbl 1119.34054
[20] Sun, C.; Feng, C., Exponential periodicity and stability of delayed neural networks, Math. Comput. Simulat., 66, 6, 469-478 (2004) · Zbl 1057.34097
[21] Wang, Z.; Liu, Y.; Liu, X., State estimation for jumping recurrent neural networks with discrete and distributed delays, Neural Netw., 22, 1, 41-48 (2009) · Zbl 1335.93125
[22] Xu, S.; Lam, J.; Ho, D. W.C., A new LMI condition for delay dependent asymptotic stability of delayed Hopfield neural networks, IEEE Trans. Circuits Syst. II, 53, 3, 230-234 (2006)
[23] Zeng, Z.; Wang, J.; Liao, X., Global exponential stability of a general class of recurrent neural networks with time-varying delays, IEEE Trans. Circuits Syst. I, 50, 10, 1353-1358 (2003) · Zbl 1368.34089
[24] Zeng, Z.; Wang, J.; Liao, X., Global asymptotic stability and global exponential stability of neural networks with unbound time-varying delays, IEEE Trans. Circuits Syst. I, 52, 3, 168-173 (2005)
[25] Zeng, Z.; Wang, J., Improved conditions for global exponential stability of recurrent neural networks with time-varying delays, IEEE Trans. Neural Netw., 17, 3, 623-635 (2006)
[26] Zhang, B.; Xu, S.; Lee, Y. Z., Improved delay-dependent exponential stability criteria for discrete-time recurrent neural networks with time-varying delays, Neurocomputing, 72, 1-3, 321-330 (2008)
[27] Zhang, H.; Wang, Z.; Liu, D., Global asymptotic stability of recurrent neural networks with multiple time-varying delays, IEEE. Trans. Neural Netw., 19, 5, 855-873 (2008)
[28] Zhang, J.; Jin, X., Global stability analysis in delayed Hopfield neural networks models, Neural Netw., 13, 7, 745-753 (2000)
[29] Zhang, Q.; Wei, X.; Xu, J., Global exponential stability of Hopfield neural networks with continuously distributed delays, Phys. Lett. A, 315, 6, 431-436 (2003) · Zbl 1038.92002
[30] Zhao, H., Global asymptotic stability of Hopfield neural network involving distributed delays, Neural Netw., 17, 1, 47-53 (2004) · Zbl 1082.68100
[31] Zhou, D.; Zhang, L.; Cao, J., On global exponential stability of cellular neural networks with Lipschitz-continuous activation function and variable delays, Appl. Math. Comput., 151, 2, 379-392 (2004) · Zbl 1077.68092
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.