TY - GEN
T1 - Memristive LSTM network hardware architecture for time-series predictive modeling problems
AU - Adam, Kazybek
AU - Smagulova, Kamilya
AU - James Pappachen, Alex
PY - 2019/1/8
Y1 - 2019/1/8
N2 - Analysis of time-series data allows to identify long term trends and make predictions that can help to improve our lives. With rapid development of artificial neural networks, long short-Tern memory (LSTM) recurrent neural network (RNN) configuration is found to be capable in dealing with time-series forecasting problems where data points are time dependent and possess seasonality trends. Gated structure of LSTM cell and flexibility in network topology (one-To-many, many-To-one, etc) allows to model systems with multiple input variables and control several parameters such as the size of look-back window to make a prediction and number of time steps to be predicted. These make LSTM attractive tool over conventional methods such as auto regression models, simple average, moving average, naive approach, ARIMA, Holts linear trend method, Holts Winter seasonal method, and others. In this paper, we propose a hardware implementation of LSTM network architecture for time-series forecasting problem. Circuit simulations were performed in LTspice using TSMC 0.18 μm CMOS technology. Software simulations were performed in Python using Keras library.
AB - Analysis of time-series data allows to identify long term trends and make predictions that can help to improve our lives. With rapid development of artificial neural networks, long short-Tern memory (LSTM) recurrent neural network (RNN) configuration is found to be capable in dealing with time-series forecasting problems where data points are time dependent and possess seasonality trends. Gated structure of LSTM cell and flexibility in network topology (one-To-many, many-To-one, etc) allows to model systems with multiple input variables and control several parameters such as the size of look-back window to make a prediction and number of time steps to be predicted. These make LSTM attractive tool over conventional methods such as auto regression models, simple average, moving average, naive approach, ARIMA, Holts linear trend method, Holts Winter seasonal method, and others. In this paper, we propose a hardware implementation of LSTM network architecture for time-series forecasting problem. Circuit simulations were performed in LTspice using TSMC 0.18 μm CMOS technology. Software simulations were performed in Python using Keras library.
KW - analog circuit
KW - crossbar
KW - LSTM
KW - memristor
KW - RNN
KW - time-series prediction
UR - http://www.scopus.com/inward/record.url?scp=85062219376&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062219376&partnerID=8YFLogxK
U2 - 10.1109/APCCAS.2018.8605649
DO - 10.1109/APCCAS.2018.8605649
M3 - Conference contribution
AN - SCOPUS:85062219376
T3 - 2018 IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2018
SP - 459
EP - 462
BT - 2018 IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2018
Y2 - 26 October 2018 through 30 October 2018
ER -