Novel Highly Nonlinear Memristive Circuit Elements for Neural Networks

被引:0
|
作者
Liu, Tong [1 ]
Kang, Yuhong [1 ]
Verma, Mohini [1 ]
Orlowski, Marius [1 ]
机构
[1] Virginia Polytech Inst & State Univ, Bradley Dept Elect & Comp Engn, Blacksburg, VA 24061 USA
关键词
memristive switches; neural hardware; nonlinear circuits; spiking neuron;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Highly nonlinear dynamics arises from novel serially and antiserially connected memristive switches. Antiserially connected memristors offer a device with built-in spiking neuron behavior. Serially connected memristors offer new functionality of a cascade of sigmoid staircase curves to represent multi-level spike-timing dependent plasticity (STDP). In a programming operation, a serial arrangement of two switches displays multiple time-delays between threshold transitions showing three distinct current levels and an arrangement of three switches four current levels spanning 6 orders of magnitude. Anti-serially connected resistive switches, aka resistive floating electrode device (RFED), can generate well-controlled spikes as a result of the history of the dynamic input. Both types of composite switches can be packed into a single intersection of a memristive crossbar architecture of 4F(2). The switches have been manufactured as a multi-stack of Cu, TaOx, Pt materials with 32 nm of oxygen-deficient TaOx in a crossbar architecture.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Circuit design and exponential stabilization of memristive neural networks
    Wen, Shiping
    Huang, Tingwen
    Zeng, Zhigang
    Chen, Yiran
    Li, Peng
    [J]. NEURAL NETWORKS, 2015, 63 : 48 - 56
  • [2] A Memristive Activation Circuit for Deep Learning Neural Networks
    Bala, Anu
    Yang, Xiaohan
    Adeyemo, Adedotun
    Jabir, Abusaleh
    [J]. PROCEEDINGS OF THE 2018 8TH INTERNATIONAL SYMPOSIUM ON EMBEDDED COMPUTING AND SYSTEM DESIGN (ISED 2018), 2018, : 1 - 5
  • [3] A Novel Memristive Chaotic Neuron Circuit and Its Application in Chaotic Neural Networks for Associative Memory
    Pan, Chaoxun
    Hong, Qinghui
    Wang, Xiaoping
    [J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2021, 40 (03) : 521 - 532
  • [4] Chaotic Circuit based on Memristive Elements
    Yu, Yongbin
    Ma, Huihui
    Yang, Chenyu
    Yang, Nijing
    Wang, Yancheng
    Wang, Xiangxiang
    Nyima, Tashi
    Wang, Mingxiao
    [J]. PROCEEDINGS OF THE 2019 14TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA 2019), 2019, : 1112 - 1116
  • [5] A Novel Memristive Neural Network Circuit and Its Application in Character Recognition
    Zhang, Xinrui
    Wang, Xiaoyuan
    Ge, Zhenyu
    Li, Zhilong
    Wu, Mingyang
    Borah, Shekharsuman
    [J]. MICROMACHINES, 2022, 13 (12)
  • [6] Study of Memristive Elements Networks
    Vourkas, Ioannis
    Sirakoulis, Georgios Ch.
    [J]. JOURNAL OF NANO RESEARCH, 2014, 27 : 5 - 14
  • [7] Global synchronization of memristive hybrid neural networks via nonlinear coupling
    Cheng-De Zheng
    Lulu Zhang
    Huaguang Zhang
    [J]. Neural Computing and Applications, 2021, 33 : 2873 - 2887
  • [8] A CMOS-based Neuron Circuit for Spiking Neural Networks with Memristive Synapse
    Liu, Hai-jun
    Li, Ji-wei
    Li, Zhi-wei
    Li, Qing-jiang
    Diao, Jie-tao
    [J]. 2018 INTERNATIONAL CONFERENCE ON COMPUTER, COMMUNICATIONS AND MECHATRONICS ENGINEERING (CCME 2018), 2018, 332 : 550 - 555
  • [9] Efficient and Low Overhead Memristive Activation Circuit for Deep Learning Neural Networks
    Bala, Anu
    Yang, Xiaohan
    Adeyemo, Adedotun
    Jabir, Abusaleh
    [J]. JOURNAL OF LOW POWER ELECTRONICS, 2019, 15 (02) : 214 - 223
  • [10] Training Neural Networks using Memristive Devices with Nonlinear Accumulative Behavior
    Piveteau, Christophe
    Le Gallo, Manuel
    Khaddam-Aljameh, Riduan
    Sebastian, Abu
    [J]. 2019 IEEE 11TH INTERNATIONAL MEMORY WORKSHOP (IMW 2019), 2019, : 120 - 123