A direct analysis method to state bounding for high‐order quaternion Hopfield neural networks with mixed delays and bounded disturbances

Abstract

The main research in this paper is the state bounding problem of high-order quaternion Hopfield neural networks (HOQHNNs) with time-varying discrete delays, unbounded distributed delays, and bounded disturbances. In the research process, firstly, the considered HOQHNNs are decomposed into four equivalent real-valued Hopfield neural networks (RHNNs) to solve the problem that quaternion multiplication is not commutative, and then, a sufficient condition related to time delays is given to ensure that the state trajectories that are contained in or globally exponentially convergent into a cuboid. Thereby, the corresponding reachable set estimation is obtained. Numerical examples are provided to illustrate validity of theoretical results. At present, the research on HOQHNNs with mixed time delays adopts Lyapunov-Krasovskii functional (LKF) method, which needs to not only choose the appropriate LKF but also take into account both conservatism and computational complexity. Besides, there is no literature to study the state bounding of HOQHNNs with mixed delays.The method suggested in the present text has three merits: (1) According to the definition of state bounding straightway, it has no use any LKF, which avoids massive calculations and solutions of high-dimensional matrix inequalities; (2) it is available not only to HOQHNNs but also to RHNNs and complex-valued Hopfield neural networks (CHNNs); and (3) make up for the blank of state bounding research of HOQHNNs. KEYWORDS direct analysis method, quaternion Hopfield neural networks, reachable set estimation, state bounding, unbounded distributed delays MSC CLASSIFICATION 93D20 INTRODUCTIONWith the intensive study of human brain, various deep learning technologies have been paid more and more attention, especially neural networks that belong to the category of artificial intelligence. The research of neural networks plays an important role in modern engineering and electronics. The Hopfield neural network was first developed in 1982. 1 It is a

Global exponential stability of quaternion bidirectional associative memory neural networks with multiple delays

“…Neural networks (NNs) have been universally employed in optimization, multi-channel audio encryption, communication security, and so on [1][2][3][4][5][6][7], which have immensely facilitated the advance of NN theory [8][9][10][11][12][13][14] in the past few years. In 1982, it is the first time for Hopfield [15] to come up with the Hopfield NN.…”

Globally asymptotic stability analysis for memristor‐based competitive systems of reaction–diffusion delayed neural networks

“…Chasing the stabilization approaches of the neural networks, one may find huge number of investigations on the above‐mentioned neural networks. As samples, we suggest the following research works and cited bibliography therein [4–35, 36–52].…”