Lin Haidan, Shen Yiran
Institute of Modern Circuits and Intelligent Information, Hangzhou Dianzi University, Hangzhou 310018, China.
Micromachines (Basel). 2023 Jan 28;14(2):337. doi: 10.3390/mi14020337.
The neuromorphic network based on artificial neurons and synapses can solve computational difficulties, and its energy efficiency is incomparable to the traditional von Neumann architecture. As a new type of circuit component, nonvolatile memristors are very similar to biological synapses in structure and function. Only one memristor can simulate the function of a synapse. Therefore, memristors provide a new way to build hardware-based artificial neural networks. To build such an artificial neural network, in addition to the artificial synapses, artificial neurons are also needed to realize the distribution of information and the adjustment of synaptic weights. As the VO volatile local active memristor is complementary to nonvolatile memristors, it can be used to simulate the function of neurons. However, determining how to better realize the function of neurons with simple circuits is one of the current key problems to be solved in this field. This paper considers the influence of distribution parameters on circuit performance under the action of high-frequency and high-speed signals. Two Mott VO memristor units are connected and coupled with microstrip lines to simulate the Hodgkin-Huxley neuron model. It is found that the proposed memristor neuron based on microstrip lines shows the characteristics of neuron action potential: amplification and threshold.
基于人工神经元和突触的神经形态网络能够解决计算难题，其能量效率是传统冯·诺依曼架构无法比拟的。作为一种新型电路元件，非易失性忆阻器在结构和功能上与生物突触非常相似。仅一个忆阻器就能模拟突触的功能。因此，忆阻器为构建基于硬件的人工神经网络提供了一种新途径。要构建这样的人工神经网络，除了人工突触外，还需要人工神经元来实现信息分布和突触权重调整。由于VO挥发性局部有源忆阻器与非易失性忆阻器互补，它可用于模拟神经元的功能。然而，确定如何用简单电路更好地实现神经元功能是该领域当前要解决的关键问题之一。本文考虑了分布参数在高频和高速信号作用下对电路性能的影响。将两个莫特VO忆阻器单元连接并与微带线耦合，以模拟霍奇金-赫胥黎神经元模型。研究发现，所提出的基于微带线的忆阻器神经元呈现出神经元动作电位的特征：放大和阈值。
