Highly Reliable Lateral Migration-Based TFT-Type Neuron Device for Spiking Neural Networks

IF 4.1 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

IEEE Electron Device Letters Pub Date : 2024-08-19 DOI:10.1109/LED.2024.3445970

Min-Kyu Park;Joon Hwang;Jong-Ho Bae;Jae-Joon Kim;Jong-Ho Lee

引用次数: 0

Abstract

A CMOS-compatible Thin Film Transistor (TFT)-type Center Path neuron device with homeostasis characteristics is proposed. By modifying the charge injection path of the gate insulator stack, the proposed neuron device operates with lateral migration, which was conventionally perceived as a disadvantage in the memory industry. Various measured electrical characteristics of the Center Path device show that directly injected charges from the channel poly-Si to the charge trap Si ₃ N ₄ with low operational voltage laterally migrate to the Si ₃ N ₄ layer above the tunneling SiO ₂ layer. Furthermore, the proposed Center Path device successfully demonstrates the integration with homeostasis functionality observed in biological neurons due to its discrete operational schemes.

查看原文本刊更多论文

用于尖峰神经网络的基于侧向迁移的高可靠性 TFT 型神经元器件

本研究提出了一种与 CMOS 兼容的薄膜晶体管 (TFT) 型中心路径神经元器件，该器件具有稳态特性。通过修改栅极绝缘体堆叠的电荷注入路径，所提出的神经元器件可在横向迁移的情况下工作，而这在存储器行业中一直被认为是一个缺点。中心路径器件的各种测量电气特性表明，在低工作电压下，从沟道多晶硅直接注入电荷阱 Si3N4 的电荷会横向迁移到隧道二氧化硅层上方的 Si3N4 层。此外，由于采用了离散的操作方案，所提出的中心路径器件成功地展示了与生物神经元中观察到的平衡功能的整合。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Electron Device Letters 工程技术-工程：电子与电气

CiteScore

8.20

自引率

10.20%

发文量

551

审稿时长

1.4 months

期刊介绍： IEEE Electron Device Letters publishes original and significant contributions relating to the theory, modeling, design, performance and reliability of electron and ion integrated circuit devices and interconnects, involving insulators, metals, organic materials, micro-plasmas, semiconductors, quantum-effect structures, vacuum devices, and emerging materials with applications in bioelectronics, biomedical electronics, computation, communications, displays, microelectromechanics, imaging, micro-actuators, nanoelectronics, optoelectronics, photovoltaics, power ICs and micro-sensors.