The issue of the global dissipativity of memristive neutral-type inertial neural networks with distributed and discrete time-varying delays is discussed without converting the original system to first-order equations. By taking some new Lyapunov–Krasovskii functionals and adopting inequality techniques, several effective criteria formulated by testable algebraic inequalities are derived to assure the global dissipativity and exponential dissipativity for the concerned models, which generalize and refine some previous results. Different from existing ones, the proposed Lyapunov–Krasovskii functionals contain not only the state variables but also their derivatives. The estimations of the globally attractive sets and globally exponentially attractive sets are also proposed. Two examples are given to validate the efficiency of the theoretical results.

讨论了具有分布和离散时变时滞的忆阻中立型惯性神经网络的全局耗散性问题，而无需将原始系统转换为一阶方程。通过采用一些新的Lyapunov–Krasovskii泛函并采用不等式技术，得出了由可检验的代数不等式制定的几个有效标准，以确保有关模型的整体耗散性和指数耗散性，从而归纳和完善了先前的结果。与现有函数不同，拟议的Lyapunov–Krasovskii泛函不仅包含状态变量，还包含其导数。还提出了对全球有吸引力的集合和全球指数有吸引力的集合的估计。给出两个例子来验证理论结果的有效性。