Memristive LSTM network hardware architecture for time-series predictive modeling problem

Abstract

Analysis of time-series data allows to identify long-term trends and make predictions that can help to improve our lives. With the rapid development of artificial neural networks, long short-term 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 the 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 autoregression models, the simple average, moving average, naive approach, ARIMA, Holt's linear trend method, Holt's Winter seasonal method, and others. In this paper, we propose a hardware implementation of LSTM network architecture for time-series forecasting problem. All simulations were performed using TSMC 0.18um CMOS technology and HP memristor model.

More by Kamilya Smagulova

• From Algorithms to Bitstreams: A Survey of FPGA-Based Acceleration for Transformer InferencePreprints.org · 2026
• Efficient and real-time perception: a survey on end-to-end event-based object detection in autonomous drivingFrontiers in Robotics and AI · 2025 · Citations: 7
• Chimera: a block-based neural architecture search framework for event-based object detectionFrontiers in Artificial Intelligence · 2025 · Citations: 4
• Adversarial Robustness and Transferability on Stochastic Resistive AcceleratorsInternational Conference on Machine Intelligence and Smart Innovation · 2025