Open AccessLow‐Voltage Oscillatory Neurons for Memristor‐Based Neuromorphic Systems
Author(s) -
Hua Qilin,
Wu Huaqiang,
Gao Bin,
Zhang Qingtian,
Wu Wei,
Li Yujia,
Wang Xiaohu,
Hu Weiguo,
Qian He
Publication year - 2019
Publication title -
global challenges
Language(s) - English
Resource type - Journals
ISSN - 2056-6646
DOI - 10.1002/gch2.201900015
Subject(s) - neuromorphic engineering , memristor , spiking neural network , voltage , oscillation (cell signaling) , computer science , synaptic weight , artificial neural network , resistor , biological system , synapse , physics , electronic engineering , materials science , topology (electrical circuits) , artificial intelligence , electrical engineering , neuroscience , engineering , chemistry , biology , biochemistry , quantum mechanics
Neuromorphic systems consisting of artificial neurons and synapses can process complex information with high efficiency to overcome the bottleneck of von Neumann architecture. Artificial neurons are essentially required to possess functions such as leaky integrate‐and‐fire and output spike. However, previous reported artificial neurons typically have high operation voltage and large leakage current, leading to significant power consumption, which is contrary to the energy‐efficient biological model. Here, an oscillatory neuron based on Ag filamentary threshold switching memristor (TS) that has a low operation voltage (<0.6 V) with ultralow power consumption (<1.8 µW) is presented. It can trigger neuronal functions, including leaky integrate‐and‐fire and threshold‐driven spiking output, with high endurance (>10 8 cycles). Being connected to an external resistor or a resistive switching memristor (RS) as synaptic weight, the TS clearly demonstrates self‐oscillation behavior once the input pulse voltage exceeds the threshold voltage. Meanwhile, the oscillation frequency is proportional to the input pulse voltage and the conductance of RS synapse, which can be used to integrate the weighted sum current. As an energy‐efficient memristor‐based spiking neural network, this combination of TS oscillatory neuron with RS synapse is further evaluated for image recognition achieving an accuracy of 79.2 ± 2.4% for CIFAR‐10 subset.