InGaZnO Optoelectronic Synaptic Transistor for Reservoir Computing and LSTM‐Based Prediction Model
Suyong Park, Seong‐Min Kim, Seong‐Min Kim, Sungjoon Kim, Sungjoon Kim, Kyungchul Park, Donghyun Ryu, Sungjun Kim, Sungjun Kim
Abstract
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.