Neural state machines (NSMs) with weight tunable synapses and leaky integrate-and-fire neurons can control the workflow according to the input information and current state, which has attracted increasing attention in handling complex control logic for various applications. The emerging memristor crossbar network provides an opportunity to further develop NSMs due to the unique analog properties, high density, low-power consumption, and high scalability. However, memristors exhibit nonideal features, such as variation, nonlinearity, and asymmetry of the conductance update, which may hinder the implementation of memristors in NSMs. In this paper, we investigate the implementation of a memristor in an NSM and demonstrate a fully memristor neural state machine (MNSM). Nonvolatile and volatile memristors are designed to emulate the synaptic and neuronal behaviors in MNSMs, respectively. Through a map search task, the MNSM not only exhibits strong robustness to the substantial nonideal behaviors of memristors but also benefits from these shortcomings, showing a faster convergence in the training process. This work proves the feasibility of applying memristors in NSMs and the great potential of MNSMs in handling complex control logic, which promotes the further development of NSMs for neuromorphic computing systems.

中文翻译：

---

高鲁棒性忆阻器神经状态机

具有权重可调节的突触和泄漏的集成发射神经元的神经状态机（NSM）可以根据输入信息和当前状态来控制工作流程，这在处理各种应用的复杂控制逻辑时引起了越来越多的关注。新兴的忆阻器纵横制网络由于其独特的模拟特性，高密度，低功耗和高可扩展性而提供了进一步开发NSM的机会。但是，忆阻器具有非理想特性，例如变化，非线性和电导更新的不对称性，这可能会阻碍忆阻器在NSM中的实现。在本文中，我们调查了忆阻器在NSM中的实现，并演示了完全忆阻器神经状态机（MNSM）。非易失性和易失性忆阻器分别设计用于模拟MNSM中的突触和神经元行为。通过地图搜索任务，MNSM不仅对忆阻器的实质非理想行为表现出强大的鲁棒性，而且还受益于这些缺点，显示出训练过程中的收敛速度更快。这项工作证明了在NSM中应用忆阻器的可行性，以及MNSM在处理复杂控制逻辑方面的巨大潜力，从而促进了用于神经形态计算系统的NSM的进一步发展。