InGaZnO Optoelectronic Synaptic Transistor for Reservoir Computing and LSTM-Based Prediction Model

Abstract

This study presents a reservoir computing (RC) system utilizing an indium gallium zinc oxide (IGZO)-based optoelectronic synaptic transistor (OST) for neuromorphic computing applications. The proposed IGZO-based OST harnesses the effects of persistent photoconductivity in the IGZO channel and charge trapping at the IGZO/tantalum oxide interface to emulate the short-term synaptic behavior. By optical stimuli, the device achieves dynamic reservoir states with nonlinear and time-dependent characteristics, enhancing its capability for temporal data processing. Moreover, the system effectively performs pattern recognition tasks, attaining high classification accuracies of 95.75% and 85.02% on the MNIST and Fashion MNIST datasets, respectively. Additionally, the device replicates nociceptive behaviors, such as allodynia and hyperalgesia, under optical stimulation, showcasing its potential for bio-inspired sensory applications. An LSTM-based prediction model is developed using Jena climate data, incorporating a method that mimics synaptic weight variation to assess its impact on performance. This approach demonstrates the feasibility of hardware-friendly neural networks via biologically inspired weight adjustments, outperforming conventional forecasting models. Notably, the model achieves a normalized root mean square error (NRMSE) as low as 0.0145, highlighting its high prediction accuracy.