https://doi.org/10.1140/epjst/e2019-900046-x
Review
A survey on LSTM memristive neural network architectures and applications
1
Nazarbayev University, 53 Kabanbay Batyr Ave., Nur-Sultan, Kazakhstan
a e-mail: apj@ieee.org
Received:
28
February
2019
Received in final form:
4
May
2019
Published online:
14
October
2019
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.
© EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature, 2019