神经形态工程学
薄膜晶体管
材料科学
光电子学
晶体管
铟
镓
无定形固体
锌
人工神经网络
纳米技术
计算机科学
电气工程
工程类
化学
人工智能
图层(电子)
冶金
电压
有机化学
作者
Yumin Yun,Junhyeong Park,Min Kong,J. Lee,Sung‐Soo Bae,Chanjin Park,Soo‐Yeon Lee
标识
DOI:10.1002/aisy.202500402
摘要
Neuromorphic computing for spiking neural networks (SNNs) has attracted tremendous attention for next‐generation computing in various applications. Amorphous indium–gallium–zinc–oxide (IGZO) is a promising candidate for optoelectronic synaptic transistors and neuron circuits due to its photoconductivity, low‐temperature fabrication process, and extremely low leakage current. Herein, an IGZO‐based optoelectronic neuromorphic system integrated with light guides is reported. The IGZO‐based optoelectronic synaptic transistor demonstrates high retention through a negative gate bias by the IGZO‐based neuron circuit and successfully emulates synaptic plasticity such as long‐term potentiation and long‐term depression. The proposed IGZO‐based neuron circuit with a double‐gate thin‐film transistor operates a dual role as a pulse generator in the programming stage and an integrate‐and‐fire neuron in the inference stage. The operation of the proposed neuron circuit through experiments and simulations is verified. The designed parameters are optimized by considering the interaction between synapses and neurons through SNN simulation with the MNIST dataset. Synapse–neuron codesign with the same fabrication in this study facilitates advancements in future optoelectronic neuromorphic systems.
科研通智能强力驱动
Strongly Powered by AbleSci AI