Memristor-Based LSTM Network with in Situ Training and its Applications


Artificial neural networks (ANNs), such as the convolutional neural network (CNN) and long short-term memory (LSTM), have high complexity and contain large numbers of parameters. Memristor-based neural networks, which have the ability of in-memory and parallel computing, are therefore proposed to accelerate the operations of ANNs. In this paper, a memristor-based hardware realization of long short-term memory (LSTM) network with in situ training is presented. The designed memristor-based LSTM (MbLSTM) network is composed of memristor-based LSTM cell and memristor-based dense layer. Sigmoid and tanh (hyperbolic tangent) activation functions are approximately implemented through intentionally designing circuit parameters. A weight update scheme with row-parallel characteristic is put forward to update the conductance of memristors in crossbars. The highlights of MbLSTM include an effective hardware-based inference process and in situ training. The validity of MbLSTM is substantiated through classification tasks. The robustness of MbLSTM to conductance variations is also analyzed.


Electrical and Computer Engineering

Second Department

Computer Science

Research Center/Lab(s)

Center for High Performance Computing Research

Second Research Center/Lab

Intelligent Systems Center


National Basic Research Program of China (973 Program), Grant 2016YFB0800402

Keywords and Phrases

Long Short-Term Memory; Memristor; Memristor-Based Neural Network; Recurrent Neural Network; Sequence Data Processing

International Standard Serial Number (ISSN)

0893-6080; 1879-2782

Document Type

Article - Journal

Document Version


File Type





© 2020 Elsevier, All rights reserved.

Publication Date

04 Aug 2020

PubMed ID