Dynamical Characteristics of a Nano-Ionic Solid Electrolyte FET Using an LSTM Model

The complexity of multi-state devices (e.g., memristors, ferroelectric RAMs (FERAMs) hinder the creation of their unified physics-based model. Data-driven approaches, such as machine learning (ML), are increasingly favored to address this challenge. In this study, we demonstrate the dynamic modelling of a synaptic ZnO/Ta<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>O<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">5</inf> Solid Electrolyte-FET by transforming its characteristics into a multivariate time-series problem based on which a Long-Short Term Memory model of the device is constructed. Our method can also be applied to other multi-state devices to accelerate the development time of Neuromorphic Computing Systems.