神经形态工程学
记忆电阻器
铁电性
人工神经网络
计算机科学
电导
电容器
材料科学
尖峰神经网络
突触可塑性
人工智能
电子工程
光电子学
电气工程
电压
物理
工程类
化学
电介质
生物化学
受体
凝聚态物理
作者
Donggang Xie,Qinchao Sun,Qianyi Geng,Jie Su,Qiang Li,Hao Ni
标识
DOI:10.1088/1361-6463/acbb12
摘要
Abstract This paper presents a ferroelectric memristor-based synaptic device with a capacitor-like structure and nonvolatile multilevel conductance. Conductance modulation can be achieved by manipulating the barrier height through polarization inversion and the mimicking of the important synaptic functions, such as long-term plasticity and spike-timing-dependent plasticity, have been implemented. By extracting device parameters, a simulated artificial neural network is constructed for image recognition, and it can achieve 91.2% recognition accuracy for Modified National Institute of Standards and Technology images. These results show the potential of this device in building brain-like computing systems and further enrich the research of ferroelectric materials in realizing artificial synapses.
科研通智能强力驱动
Strongly Powered by AbleSci AI