In this paper, we consider a class of quaternion-valued inertial neural networks with time-varying delays. First, by applying a continuation theorem of coincidence degree theory, we establish the existence of anti-periodic solutions of the considered neural networks. Second, by choosing a proper variable substitution, we transform the neural networks into a system of first order differential equations, and by constructing a suitable Lyapunov function, we derive a set of sufficient conditions ensuring the global exponential stability of the system. Finally, we give two examples to illustrate the effectiveness of our results.
YoungS., ScottP., NasrabadiN., Object recognition using multilayer Hopfield neural network, IEEE Trans Image Process6 (1997), 357–372.
2.
AtenciaM., JoyaG., SandovalF., Dynamical analysis of continuous higher order Hopfield neural networks for combinatorial optimization, Neural Comput17 (2005), 1802–1819.
3.
HopfieldJ., Neurons with graded response have collective computational properties like those of two-state neurons, in: Proceedings of National Academy of Sciences, USA,81(10) (1984), 3088–3092in.
4.
DiresscheP., ZouX., Global attractivity in delayed Hopfield neural network models, SIAM J Appl Math58 (1998), 1878–1890.
5.
de JesúsR.J., Discrete time control based in neural networks for pendulums, Appl Soft Comput68 (2018), 821–832.
6.
FouratiF., Multiple neural control and stabilization, Neural Comput Appl29(12) (2018), 1435–1442.
7.
RubioJ.J., Modified optimal control with a back propagation network for robotic arms, IET Control Theory A6(14) (2012), 2216–2225.
8.
YogambigaiJ., AliM.S., ZhuQ., CaiJ., Exponential lagrange stability for markovian jump uncertain neural networks with leakage delay and mixed time-varying delays via impulsive control, Math Probl Eng2018 (2018), Article ID 6489517, 15 pages.
9.
de JesúsR.J., LughoferE., Meda-CampañaJ.A., PáramoL.A., NovoaJ.F. and PachecoJ., Neural network updating via argument Kalman filter for modeling of Takagi-Sugeno fuzzy models, J Intell Fuzzy Syst35(2) (2018), 2585–2596.
10.
MengX.L., ShiF.G., YaoJ.C., An inequality approach for evaluating decision making units with a fuzzy output, J Intell Fuzzy Syst34(1) (2018), 459–465.
ZhangX.M., HanQ.L., State estimation for static neural networks with time-varying delays based on an improved reciprocally convex inequality, IEEE Trans Neural Netw Learn Syst29(4) (2018), 1376–1381.
13.
BabcockK.L., WesterveltR.M., Stability and dynamics of simple electronic neural networks with added inertia, Physica D Nonlinear Phenom23 (1986), 464–469.
14.
AshmoreJ.F., AttwellD., Models for electrical tuning in hair cells, Proc R Soc Lond B226 (1985), 325–344.
15.
AngelakiD.E., CorreiaM.J., Models of membrane resonance in pigeon semicircular canal type II hair cells, Biol Cybern65 (1991), 1–10.
16.
WangF., HelianN., WuS., LimM., GuoY., ParkerA., Delayed switching in memristors and memristive systems, IEEE Electr Device Lett31 (2010), 755–757.
17.
KeY., MiaoC., Anti-periodic solutions of inertial neural networks with time delays, Neural Process Lett45(2) (2017), 523–538.
18.
CaoJ., WanY., Matrix measure strategies for stability and synchronization of inertial BAM neural network with time delays, Neural Netw53 (2014), 165–172.
19.
KeY., MiaoC., Stability analysis of inertial Cohen-Grossberg-type neural networks with time delays, Neurocomputing117 (2013), 196–205.
20.
KeY., MiaoC., Stability and existence of periodic solutions in inertial BAM neural networks with time delay, Neural Comput Appl23 (2013), 1089–1099.
21.
DharaniaS., RakkiyappanaR., ParkJ.H., Pinning sampled-data synchronization of coupled inertial neural networks with reaction-diffusion terms and time-varying delays, Neurocomputing227 (2017), 101–107.
22.
ZhangG., ZengZ., HuJ., New results on global exponential dissipativity analysis of memristive inertial neural networks with distributed time-varying delays, Neural Netw97 (2018), 183–191.
23.
SudberyA., Quaternionic analysis, Math Proc Camb Phil Soc85(2) (1979), 199–225.
KristiansenR., NicklassonP.J., GravdahlJ.T., Satellite attitude control by quaternionbased backstepping, In American Control Conference, 2005. Proceedings of the 2005, pp. 907–912, IEEE. Portland, 2005.
26.
WangX.Y., WangC.P., YangH.Y., NiuP.P., A robust blind color image watermarking in quaternion fourier transform domain, J Syst Software86(2) (2013), 255–277.
27.
VinceJ., Quaternions for Computer Graphics, Springer-Verlag, London: 2011.
28.
EllT.A., Le BihanN. and SangwineS.J., Quaternion Fourier transforms for signal and image processing, John Wiley & Sons, New Jersey, 2014.
29.
IsokawaT., MatsuiN., NishimuraH., Quaternionic neural networks: fundamental properties and applications, In: NittaT. (ed.) Complex Valued Neural Networks: Utilizing High-Dimensional Parameters, chap. XVI, pp. 411–439. Information Science Reference, Hershey, New York, 2009.
30.
MatsuiN., IsokawaT., KusamichiH., PeperF., NishimuraH., Quaternion neural network with geometrical operators, J Intell Fuzzy Syst Appl Eng Technol15(3-4) (2004), 149–164.
31.
KusamichiH., IsokawaT., MatsuiN., OgawaY., MaedaK., A new scheme for colour night vision by quaternion neural network, In proceedings of the 2nd International Conference on Autonomous Robots and Agents, Palmerston North, New Zealand, 2004.
32.
LiuY., ZhangD., LuJ., Global exponential stability for quaternion-valued recurrent neural networks with time-varying delays, Nonlinear Dyn87 (2017), 553–565.
33.
ZhangD.D., KouK.I., LiuY., CaoJ.D., Decomposition approach to the stability of recurrent neural netwoks with asynchronous time delays in quaternion field, Neurel Netw94 (2017), 55–66.
34.
LiY.K., MengX.F., Existence and global exponential stability of pseudo almost periodic solutions for neutral type quaternion-valued neural networks with delays in the leakage term on time scales, Complexity2017 (2017), Article ID 9878369, 15 pages.
35.
PopaC.A., KaslikE., Multistability and multiperiodicity in impulsive hybrid quaternion-valued neural networks with mixed delays, Neural Netw99 (2018), 1–18.
36.
ShuH., SongQ., LiuY., ZhaoZ., AlsaadiF.E., Global μ-stability of quaternion-valued neural networks with non-differentiable time-varying delays, Neurocomputing247 (2017), 202–212.
37.
HuJ., ZengC., TanJ., Boundedness and periodicity for linear threshold discrete-time quaternion-valued neural network with time-delays, Neurocomputing267 (2017), 417–425.
38.
LiY., QinJ., Existence and global exponential stability of periodic solutions for quaternion-valued cellular neural networks with time-varying delays, Neurocomputing292 (2018), 91–103.
39.
LiY., MengX., YeY., Almost periodic synchronization for quaternion-valued neural networks with time-varying delays, Complexity2018 (2018), Article ID 6504590, 16 pages.
40.
WangQ., FangY., LiH., SuL., DaiB., Anti-periodic solutions for high-order Hopfield neural networks with impulses, Neurocomputing138 (2014), 339–346.
41.
LiY.K., SuJ.Y., Anti-periodic solutions to impulsive shunting inhibitory cellular neural networks with distributed delays on time scales, Commun Nonlinear Sci Numer Simulat16 (2011), 3326–3336.
42.
LiY.K., YangL., WuW.Q., Anti-periodic solution for impulsive BAM neural networks with time-varying leakage delays on time scales, Neurocomputing149 (2015), 536–545.
43.
ŞaylıM. and YılmazE., Anti-periodic solutions for state-dependent impulsive recurrent neural networks with time-varying and continuously distributed delays, Ann Oper Res258(1) (2017), 159–185.
44.
XuC., LiP., On anti-periodic solutions for neutral shunting inhibitory cellular neural networks with time-varying delays andoperator, Neurocomputing275 (2018), 377–382.
45.
ShiP., DongL., Existence and exponential stability of anti-periodic solutions of Hopfield neural networks with impulses, Appl Math Comput216(2) (2010), 623–630.
46.
LongZ., New results on anti-periodic solutions for SICNNs with oscillating coefficients in leakage terms, Neurocomputing171 (2016), 503–509.
47.
PengL., WangW., Anti-periodic solutions for shunting inhibitory cellular neural networks with time-varying delays in leakage terms, Neurocomputing111 (2013), 27–33.
48.
ShaoJ., Anti-periodic solutions for shunting inhibitory cellular neural networks with time-varying delays, Phys Lett A372(30) (2008), 5011–5016.
49.
AmsterP., Topological Methods in the Study of Boundary Valued Problems, Springer, New York, 2013.
