IDEAS home Printed from https://ideas.repec.org/a/wsi/fracta/v31y2023i06ns0218348x23400406.html
   My bibliography  Save this article

Memristor-Based Lstm Network For Text Classification

Author

Listed:
  • GANG DOU

    (The College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, P. R. China)

  • KAIXUAN ZHAO

    (The College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, P. R. China)

  • MEI GUO

    (The College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, P. R. China)

  • JUN MOU

    (��School of Information Science and Engineering, Dalian Polytechnic University, Dalian 116034, P. R. China)

Abstract

Long short-term memory (LSTM) with significantly increased complexity and a large number of parameters have a bottleneck in computing power resulting from limited memory capacity. Hardware acceleration of LSTM using memristor circuit is an effective solution. This paper presents a complete design of memristive LSTM network system. Both the LSTM cell and the fully connected layer circuit are implemented through memristor crossbars, and the 1T1R design avoids the influence of the sneak current which helps to improve the accuracy of network calculation. To reduce the power consumption, the word embedding dimensionality was reduced using the GloVe model, and the number of features in the hidden layer was reduced. The effectiveness of the proposed scheme is verified by performing the text classification task on the IMDB dataset and the hardware training accuracy reached as high as 88.58%.

Suggested Citation

  • Gang Dou & Kaixuan Zhao & Mei Guo & Jun Mou, 2023. "Memristor-Based Lstm Network For Text Classification," FRACTALS (fractals), World Scientific Publishing Co. Pte. Ltd., vol. 31(06), pages 1-12.
    • Handle: RePEc:wsi:fracta:v:31:y:2023:i:06:n:s0218348x23400406
    DOI: 10.1142/S0218348X23400406
    as

    Download full text from publisher

    File URL: http://www.worldscientific.com/doi/abs/10.1142/S0218348X23400406
    Download Restriction: Access to full text is restricted to subscribers
    File URL: https://libkey.io/10.1142/S0218348X23400406?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Li, Zongxiang & Li, Liwei & Chen, Jing & Wang, Dongqing, 2024. "A multi-head attention mechanism aided hybrid network for identifying batteries’ state of charge," Energy, Elsevier, vol. 286(C).
    2. Chen, Xiongjian & Wang, Ning & Wang, Yiteng & Wu, Huagan & Xu, Quan, 2023. "Memristor initial-offset boosting and its bifurcation mechanism in a memristive FitzHugh-Nagumo neuron model with hidden dynamics," Chaos, Solitons & Fractals, Elsevier, vol. 174(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:wsi:fracta:v:31:y:2023:i:06:n:s0218348x23400406. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Tai Tone Lim (email available below). General contact details of provider: https://www.worldscientific.com/worldscinet/fractals .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.