A survey on LSTM memristive neural network architectures and applications

Kamilya Smagulova, Alex Pappachen James

Research output: Contribution to journalReview article

1 Citation (Scopus)

Abstract

The recurrent neural networks (RNN) found to be an effective tool for approximating dynamic systems dealing with time and order dependent data such as video, audio and others. Long short-term memory (LSTM) is a recurrent neural network with a state memory and multilayer cell structure. Hardware acceleration of LSTM using memristor circuit is an emerging topic of study. In this work, we look at history and reasons why LSTM neural network has been developed. We provide a tutorial survey on the existing LSTM methods and highlight the recent developments in memristive LSTM architectures.

Original languageEnglish
Pages (from-to)2313-2324
Number of pages12
JournalEuropean Physical Journal: Special Topics
Volume228
Issue number10
DOIs
Publication statusPublished - Oct 1 2019

    Fingerprint

ASJC Scopus subject areas

  • Materials Science(all)
  • Physics and Astronomy(all)
  • Physical and Theoretical Chemistry

Cite this