Full-Analog Reservoir Computing Circuit Based on Memristor With a Hybrid Wide-Deep Architecture

被引:3
|
作者
Chen, Liangyu [1 ,2 ]
Wang, Xiaoping [1 ,2 ]
Yang, Chao [2 ,3 ,4 ]
Chen, Zhanfei [2 ]
Zhang, Junming [1 ,5 ]
Zeng, Zhigang [1 ,2 ]
机构
[1] Huazhong Univ Sci & Technol, Sch Artificial Intelligence & Automat, Wuhan 430074, Peoples R China
[2] Huazhong Univ Sci & Technol, Key Lab Image Proc & Intelligent Control, Educ Minist China, Wuhan 430074, Peoples R China
[3] Huazhong Univ Sci & Technol, Inst Artificial Intelligence, Sch Artificial Intelligence & Automat, Wuhan 430074, Peoples R China
[4] Guangxi Univ Sci & Technol, Sch Comp Sci & Technol, Liuzhou 545006, Peoples R China
[5] Huazhong Univ Sci & Technol, Sch Integrated Circuits, Wuhan 430074, Peoples R China
基金
中国国家自然科学基金;
关键词
Reservoir computing; memristor; neuromorphic architecture; arrhythmia detection; analog circuit design; CHAOTIC NEURAL-NETWORKS; IN-MEMORY; CROSSBAR ARRAY; HARDWARE; CLASSIFICATION; COMPUTATION; DESIGN; MODEL; EDGE;
D O I
10.1109/TCSI.2023.3334267
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Reservoir computing (RC) contains two significant variants: wide RC and deep RC. The hybrid wide-deep architecture absorbs their strengths with a powerful parallel processing capability while enhancing the memory capacity of reservoirs. However, the fully analog RC circuit combining the two structures has yet to be proposed, mainly due to unmanageable hierarchical signal processing. Here we report a full-analog memristive RC circuit with a hybrid wide-deep architecture comprising an input module, mask module, reservoir module, and readout module. The input module can generate continuous voltages with temporal sequences. The mask module provides parallel mask processes, laying the foundation for implementing a wide RC structure. The reservoir module includes dynamic memristors and postprocessing circuits. Dynamic memristors can produce high-dimensional reservoir states, and postprocessing circuits allow memristive reservoir circuits to be cascaded to achieve a deep RC structure. The readout module mainly consists of a nonvolatile memristor crossbar and an analog integrator, enabling an efficient multiplication-and-accumulation operation. The simulation results in LTspice illustrate that the memory capacity of the proposed circuit is 91.6% higher than that of wide RC. Moreover, it can efficiently perform temporal tasks, obtaining a high accuracy of 98.99% in arrhythmia detection.
引用
收藏
页码:501 / 514
页数:14
相关论文
共 5 条
  • [1] Photoelectric Reservoir Computing Based on TiO x Memristor for Analog Signal Processing
    Li, Zimu
    Gu, Dengshun
    Xie, Xuesen
    Li, Ping
    Sun, Bai
    Liao, Changrong
    Hu, Xiaofang
    Yan, Jia
    Wang, Lidan
    Duan, Shukai
    Zhou, Guangdong
    ACS APPLIED NANO MATERIALS, 2025, 8 (13) : 6591 - 6603
  • [2] Memristor-based Deep Spiking Neural Network with a Computing-In-Memory Architecture
    Nowshin, Fabiha
    Yi, Yang
    PROCEEDINGS OF THE TWENTY THIRD INTERNATIONAL SYMPOSIUM ON QUALITY ELECTRONIC DESIGN (ISQED 2022), 2022, : 163 - 168
  • [3] Deep reservoir computing based on self-rectifying memristor synapse for time series prediction
    Wang, Rui
    Liang, Qi
    Wang, Saisai
    Cao, Yaxiong
    Ma, Xiaohua
    Wang, Hong
    Hao, Yue
    APPLIED PHYSICS LETTERS, 2023, 123 (04)
  • [4] Hardware Implementation of Next Generation Reservoir Computing with RRAM-Based Hybrid Digital-Analog System
    Dong, Danian
    Zhang, Woyu
    Xie, Yuanlu
    Yue, Jinshan
    Ren, Kuan
    Huang, Hongjian
    Zheng, Xu
    Sun, Wen Xuan
    Lai, Jin Ru
    Fan, Shaoyang
    Wang, Hongzhou
    Yu, Zhaoan
    Yao, Zhihong
    Xu, Xiaoxin
    Shang, Dashan
    Liu, Ming
    ADVANCED INTELLIGENT SYSTEMS, 2024, 6 (10)
  • [5] New Memristor-Based Crossbar Array Architecture with 50-% Area Reduction and 48-% Power Saving for Matrix-Vector Multiplication of Analog Neuromorphic Computing
    Son Ngoc Truong
    Min, Kyeong-Sik
    JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE, 2014, 14 (03) : 356 - 363