A survey on LSTM memristive neural network architectures and applications

• Published in: The European physical journal. ST, Special topics Vol. 228; no. 10; pp. 2313 - 2324
• Main Authors: Smagulova, Kamilya, James, Alex Pappachen
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-10-2019; Springer Nature B.V
• Subjects: Acceleration; Atomic; Audio data; Circuits; Classical and Continuum Physics; Condensed Matter Physics; Dynamics and Applications; Materials Science; Measurement Science and Instrumentation; Memristor-based Systems: Nonlinearity; Memristors; Molecular; Multilayers; Neural networks; Optical and Plasma Physics; Physics; Physics and Astronomy; Recurrent neural networks; Review; System effectiveness; Time dependence
• ISSN: 1951-6355; 1951-6401
• DOI: 10.1140/epjst/e2019-900046-x

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.