Global exponential stability of octonion-valued neural networks with leakage delay and mixed delays. (English) Zbl 1441.93249
Summary: This paper discusses octonion-valued neural networks (OVNNs) with leakage delay, time-varying delays, and distributed delays, for which the states, weights, and activation functions belong to the normed division algebra of octonions. The octonion algebra is a nonassociative and noncommutative generalization of the complex and quaternion algebras, but does not belong to the category of Clifford algebras, which are associative. In order to avoid the nonassociativity of the octonion algebra and also the noncommutativity of the quaternion algebra, the Cayley-Dickson construction is used to decompose the OVNNs into 4 complex-valued systems. By using appropriate Lyapunov-Krasovskii functionals, with double and triple integral terms, the free weighting matrix method, and simple and double integral Jensen inequalities, delay-dependent criteria are established for the exponential stability of the considered OVNNs. The criteria are given in terms of complex-valued linear matrix inequalities, for two types of Lipschitz conditions which are assumed to be satisfied by the octonion-valued activation functions. Finally, two numerical examples illustrate the feasibility, effectiveness, and correctness of the theoretical results.
Keywords:
octonion-valued neural networks; distributed delays; global stability; linear matrix inequalitiesReferences:
| [1] | Arena, P.; Fortuna, L.; Muscato, G.; Xibilia, M., (Neural networks in multidimensional domains, Fundamentals and new trends in modelling and control. Neural networks in multidimensional domains, Fundamentals and new trends in modelling and control, Lecture notes in control and information sciences, vol. 234 (1998), Springer London) · Zbl 0910.68167 |
| [2] | Arena, P.; Fortuna, L.; Occhipinti, L.; Xibilia, M., Neural networks for quaternion-valued function approximation, (International symposium on circuits and systems, Vol. 6 (1994), IEEE), 307-310 |
| [3] | Bauer, S.; Leon, F. P., Hyperspectral fluorescence data fusion using quaternion and octonion phase, (2016 IEEE international conference on multisensor fusion and integration for intelligent systems (MFI) (2016), IEEE) |
| [4] | Błaszczyk, Ł.; Snopek, K. M., Octonion Fourier transform of real-valued functions of three variables - selected properties and examples, Signal Processing, 136, 29-37 (2017) |
| [5] | Buchholz, S.; Le Bihan, N., Polarized signal classification by complex and quaternionic multi-layer perceptrons, International Journal of Neural Systems, 18, 2, 75-85 (2008) |
| [6] | Buchholz, S.; Sommer, G., On Clifford neurons and Clifford multi-layer perceptrons, Neural Networks, 21, 7, 925-935 (2008) · Zbl 1254.92002 |
| [7] | Chanyal, B. C., Octonion massive electrodynamics, General Relativity and Gravitation, 46, 1 (2013) · Zbl 1286.83031 |
| [8] | Chanyal, B. C.; Bisht, P. S.; Li, T.; Negi, O. P.S., Octonion quantum chromodynamics, International Journal of Theoeretical Physics, 51, 11, 3410-3422 (2012) · Zbl 1263.81268 |
| [9] | Chanyal, B. C.; Bisht, P. S.; Negi, O. P.S., Generalized octonion electrodynamics, International Journal of Theoeretical Physics, 49, 6, 1333-1343 (2010) · Zbl 1194.81312 |
| [10] | Chanyal, B. C.; Bisht, P. S.; Negi, O. P.S., Generalized split-octonion electrodynamics, International Journal of Theoeretical Physics, 50, 6, 1919-1926 (2011) · Zbl 1225.81147 |
| [11] | Chen, X.; Li, Z.; Song, Q.; Hu, J.; Tan, Y., Robust stability analysis of quaternion-valued neural networks with time delays and parameter uncertainties, Neural Networks, 91, 55-65 (2017) · Zbl 1443.34075 |
| [12] | Chen, X.; Song, Q., Global stability of complex-valued neural networks with both leakage time delay and discrete time delay on time scales, Neurocomputing, 121, 254-264 (2013) |
| [13] | Chen, X.; Song, Q.; Li, Z., Design and analysis of quaternion-valued neural networks for associative memories, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 1-10 (2017) |
| [14] | Chen, X.; Song, Q.; Liu, X.; Zhao, Z., Global \(\mu \)-stability of complex-valued neural networks with unbounded time-varying delays, Abstract and Applied Analysis, 2014, 1-9 (2014) · Zbl 1470.34195 |
| [15] | Chen, X.; Song, Q.; Liu, Y.; Zhao, Z., Global \(\mu \)-stability of impulsive complex-valued neural networks with leakage delay and mixed delays, Abstract and Applied Analysis, 2014, 1-14 (2014) · Zbl 1470.34196 |
| [16] | Chen, X.; Song, Q.; Zhao, Z.; Liu, Y., Global \(\mu \) -stability analysis of discrete-time complex-valued neural networks with leakage delay and mixed delays, Neurocomputing, 175, 723-735 (2016) |
| [17] | Demir, S., Hyperbolic octonion formulation of gravitational field equations, International Journal of Theoeretical Physics, 52, 1, 105-116 (2012) · Zbl 1263.83059 |
| [18] | Demir, S.; Tanişli, M., Hyperbolic octonion formulation of the fluid Maxwell equations, Journal of the Korean Physical Society, 68, 5, 616-623 (2016) |
| [19] | Dray, T.; Manogue, C., The geometry of the octonions (2015), World Scientific · Zbl 1333.17004 |
| [20] | Fang, T.; Sun, J., Stability of complex-valued recurrent neural networks with time-delays, IEEE Transactions on Neural Networks and Learning Systems, 25, 9, 1709-1713 (2014) |
| [21] | Gao, H.-Y.; Lam, K.-M., From quaternion to octonion: Feature-based image saliency detection, (2014 IEEE international conference on acoustics, speech and signal processing (2014), IEEE) |
| [22] | Gao, H.-Y.; Lam, K.-M., Salient object detection using octonion with bayesian inference, (2014 IEEE international conference on image processing (2014), IEEE) |
| [23] | Gong, W.; Liang, J.; Cao, J., Global \(\mu \)-stability of complex-valued delayed neural networks with leakage delay, Neurocomputing, 168, 135-144 (2015) |
| [24] | Hirose, A., Complex-valued neural networks, Studies in computational intelligence (2012), Springer Berlin Heidelberg · Zbl 1235.68016 |
| [25] | Hirose, A., Complex-valued neural networks: Advances and applications (2013), John Wiley & Sons, Inc · Zbl 1388.68009 |
| [26] | Hu, J.; Wang, J., Global stability of complex-valued recurrent neural networks with time-delays, IEEE Transactions on Neural Networks and Learning Systems, 23, 6, 853-865 (2012) |
| [27] | Hu, J.; Wang, J., Global exponential periodicity and stability of discrete-time complex-valued recurrent neural networks with time-delays, Neural Networks, 66, 119-130 (2015) · Zbl 1395.37056 |
| [28] | Isokawa, T.; Kusakabe, T.; Matsui, N.; Peper, F., Quaternion neural network and its application, (Palade, V.; Howlett, R.; Jai, ., Knowledge-based intelligent information and engineering systems. Knowledge-based intelligent information and engineering systems, Lecture notes in computer science, vol. 2774 (2003)), 318-324 · Zbl 1048.68871 |
| [29] | Jahanchahi, C.; Took, C.; Mandic, D., On HR calculus, quaternion valued stochastic gradient, and adaptive three dimensional wind forecasting, (International joint conference on neural networks (2010), IEEE), 1-5 |
| [30] | Koplinger, J., Dirac equation on hyperbolic octonions, Applied Mathematics and Computation, 182, 1, 443-446 (2006) · Zbl 1134.81357 |
| [31] | Kuroe, Y.; Tanigawa, S.; Iima, H., Models of Hopfield-type Clifford neural networks and their energy functions –hyperbolic and dual valued networks -, (International conference on neural information processing. International conference on neural information processing, Lecture notes in computer science, vol. 7062 (2011)), 560-569 |
| [32] | Kusamichi, H., Isokawa, T., Matsui, N., Ogawa, Y., & Maeda, K. (2004), A new scheme for color night vision by quaternion neural network. In: International conference on autonomous robots and agents (pp. 101-106). |
| [33] | Liu, X.; Chen, T., Global exponential stability for complex-valued recurrent neural networks with asynchronous time delays, IEEE Transactions on Neural Networks and Learning Systems, 27, 3, 593-606 (2016) |
| [34] | Liu, Y.; Xu, P.; Lu, J.; Liang, J., Global stability of Clifford-valued recurrent neural networks with time delays, Nonlinear Dynamics, 84, 2, 767-777 (2015) · Zbl 1354.93132 |
| [35] | Liu, Y.; Zhang, D.; Lou, J.; Lu, J.; Cao, J., Stability analysis of quaternion-valued neural networks: Decomposition and direct approaches, IEEE Transactions on Neural Networks and Learning Systems, 1-11 (2017) |
| [36] | Liu, Y.; Zhang, D.; Lu, J., Global exponential stability for quaternion-valued recurrent neural networks with time-varying delays, Nonlinear Dynamics, 87, 1, 553-565 (2016) · Zbl 1371.93098 |
| [37] | Liu, Y.; Zhang, D.; Lu, J.; Cao, J., Global \(\mu \)-stability criteria for quaternion-valued neural networks with unbounded time-varying delays, Information Sciences, 360, 273-288 (2016) · Zbl 1450.34050 |
| [38] | Mostafa, M.; Teich, W. G.; Lindner, J., Local stability analysis of discrete-time, continuous-state, complex-valued recurrent neural networks with inner state feedback, IEEE Transactions on Neural Networks and Learning Systems, 25, 4, 830-836 (2014) |
| [39] | Okubo, S., Introduction to octonion and other non-associative algebras in physics (1995), Cambridge University Press · Zbl 0841.17001 |
| [40] | Pan, J.; Liu, X.; Xie, W., Exponential stability of a class of complex-valued neural networks with time-varying delays, Neurocomputing, 164, 293-299 (2015) |
| [41] | Pearson, J.; Bisset, D., Back propagation in a Clifford algebra, (International conference on artificial neural networks, Vol. 2 (1992)), 413-416 |
| [42] | Pearson, J.; Bisset, D., Neural networks in the Clifford domain, (International conference on neural networks, Vol. 3 (1994), IEEE), 1465-1469 |
| [43] | Popa, C.-A., Octonion-valued neural networks, (Artificial neural networks and machine learning (2016)), 435-443 |
| [44] | Popa, C.-A.; Kaslik, E., Multistability and multiperiodicity in impulsive hybrid quaternion-valued neural networks with mixed delays, Neural Networks, 99, 1-18 (2018) · Zbl 1448.93275 |
| [45] | Rakkiyappan, R.; Velmurugan, G.; Li, X., Complete stability analysis of complex-valued neural networks with time delays and impulses, Neural Processing Letters, 41, 3, 435-468 (2014) |
| [46] | Shu, H.; Song, Q.; Liu, Y.; Zhao, Z.; Alsaadi, F. E., Global \(\mu \) - stability of quaternion-valued neural networks with non-differentiable time-varying delays, Neurocomputing, 247, 202-212 (2017) |
| [47] | Snopek, K. M., Quaternions and octonions in signal processing –fundamentals and some new results, Przeglad Telekomunikacyjny + Wiadomosci Telekomunikacyjne, 6, 618-622 (2015) |
| [48] | Song, Q.; Yan, H.; Zhao, Z.; Liu, Y., Global exponential stability of complex-valued neural networks with both time-varying delays and impulsive effects, Neural Networks, 79, 108-116 (2016) · Zbl 1417.34180 |
| [49] | Song, Q.; Yan, H.; Zhao, Z.; Liu, Y., Global exponential stability of impulsive complex-valued neural networks with both asynchronous time-varying and continuously distributed delays, Neural Networks, 81, 1-10 (2016) · Zbl 1417.34181 |
| [50] | Song, Q.; Zhao, Z., Stability criterion of complex-valued neural networks with both leakage delay and time-varying delays on time scales, Neurocomputing, 171, 179-184 (2016) |
| [51] | Song, Q.; Zhao, Z.; Liu, Y., Impulsive effects on stability of discrete-time complex-valued neural networks with both discrete and distributed time-varying delays, Neurocomputing, 168, 1044-1050 (2015) |
| [52] | Subramanian, K.; Muthukumar, P., Global asymptotic stability of complex-valued neural networks with additive time-varying delays, Cognitive Neurodynamics, 11, 3, 293-306 (2017) |
| [53] | Took, C.; Mandic, D.; Aihara, K., Quaternion-valued short term forecasting of wind profile, (International joint conference on neural networks (2010), IEEE), 1-6 |
| [54] | Velmurugan, G.; Rakkiyappan, R.; Cao, J., Further analysis of global \(\mu \)-stability of complex-valued neural networks with unbounded time-varying delays, Neural Networks, 67, 14-27 (2015) · Zbl 1398.34103 |
| [55] | Velmurugan, G.; Rakkiyappan, R.; Lakshmanan, S., Passivity analysis of memristor-based complex-valued neural networks with time-varying delays, Neural Processing Letters, 42, 3, 517-540 (2014) |
| [56] | Wang, R.; Xiang, G.; Zhang, F., L1-norm minimization for octonion signals, (2016 international conference on audio, language and image processing (2016), IEEE) |
| [57] | Widrow, B.; McCool, J.; Ball, M., The complex LMS algorithm, Proceedings of the IEEE, 63, 4, 719-720 (1975) |
| [58] | Xu, X.; Zhang, J.; Shi, J., Exponential stability of complex-valued neural networks with mixed delays, Neurocomputing, 128, 483-490 (2014) |
| [59] | Yang, R.; Wu, B.; Liu, Y., A Halanay-type inequality approach to the stability analysis of discrete-time neural networks with delays, Applied Mathematics and Computation, 265, 696-707 (2015) · Zbl 1410.39032 |
| [60] | Zhang, C.-K.; He, Y.; Jiang, L.; Wu, M., Stability analysis for delayed neural networks considering both conservativeness and complexity, IEEE Transactions on Neural Networks and Learning Systems, 27, 7, 1486-1501 (2016) |
| [61] | Zhang, D.; Kou, K. I.; Liu, Y.; Cao, J., Decomposition approach to the stability of recurrent neural networks with asynchronous time delays in quaternion field, Neural Networks, 94, 55-66 (2017) · Zbl 1437.93112 |
| [62] | Zhang, Z.; Lin, C.; Chen, B., Global stability criterion for delayed complex-valued recurrent neural networks, IEEE Transactions on Neural Networks and Learning Systems, 25, 9, 1704-1708 (2014) |
| [63] | Zhang, Z.; Liu, X.; Chen, J.; Guo, R.; Zhou, S., Further stability analysis for delayed complex-valued recurrent neural networks, Neurocomputing, 251, 81-89 (2017) |
| [64] | Zhou, B.; Song, Q., Boundedness and complete stability of complex-valued neural networks with time delay, IEEE Transactions on Neural Networks and Learning Systems, 24, 8, 1227-1238 (2013) |
| [65] | Zhu, J.; Sun, J., Global exponential stability of Clifford-valued recurrent neural networks, Neurocomputing, 173, 685-689 (2016) |
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.
