Anti-synchronization for stochastic memristor-based neural networks with non-modeled dynamics via adaptive control approach

Abstract

In this paper, exponential anti-synchronization in mean square of an uncertain memristor-based neural network is studied. The uncertain terms include non-modeled dynamics with boundary and stochastic perturbations. Based on the differential inclusions theory, linear matrix inequalities, Gronwall's inequality and adaptive control technique, an adaptive controller with update laws is developed to realize the exponential anti-synchronization. Adaptive controller can adjust itself behavior to get the best performance, according to the environment is changing or the environment has changed, which has the ability to adapt to environmental change. Furthermore, a numerical example is provided to validate the effectiveness of the proposed method.

Finite-time anti-synchronization of memristive stochastic BAM neural networks with probabilistic time-varying delays

“…Combine with the Assumption 1 and controller (9), we get stable in the mean square via the controllers (9), if there exists the gain constants qx, qy and kx, ky such that It should be mentioned that no complex numerical calculation such as computing redundance algebraic criterions [58] or solving linear matrix inequality (LMIs) [59,60] is needed in the anti-synchronization conditions. Thus, our anti-synchronization consequences have a wider adaptive capability and more successful application.…”

Global $$O(t^{-\alpha })$$ O ( t - α ) stabilization of fractional-order memristive neural networks with time delays

“… 2012 ; Wu and Zeng 2012 ; Wen and Zeng 2012 ; Zhao et al. 2015 ). From the description of memristive neural networks, combining memristors with infinite memory is extremely interesting.…”

A universal emulator for memristor, memcapacitor, and meminductor and its chaotic circuit

“…3 Memristor, memcapacitor, and meminductor are collectively referred to as mem-elements. 42 The unique memory characteristics and nanoscale structures of these three mem-elements have a wide application prospect in non-volatile memory, 4 artificial neural networks, [5][6][7][8][9][10] and chaotic circuits. [11][12][13][14][15] However, due to the cost and technical difficulties of nanoscale device manufacturing, commercially available mem-elements will be impossible in the near future.…”