人工神经网络
MOSFET
计算机科学
电压
集合(抽象数据类型)
芯(光纤)
阈值电压
数据建模
工作(物理)
电子工程
模拟
人工智能
电气工程
工程类
晶体管
电信
机械工程
数据库
程序设计语言
作者
Shuhan Wang,Zheng Zhou,Xiaoyan Liu,Xing Zhang
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2024-03-17
卷期号:: 1-3
被引量:1
标识
DOI:10.1109/cstic61820.2024.10531825
摘要
Tiny neural network (NN) modeling physical effects inside MOSFET is demonstrated in this work. BSIM-IMG and HSPICE are used to generation datasets, which samples above 20000. Physical effects, Threshold Voltage Roll-off (TVR) and DIBL, are set as NN modeling goal and achieved >99% and >92% fitting accuracy respectively (@ 5-100-100-42 FCN, 15 training epochs). The conception of cooperation between multi NN-based sub-model and BSIM core-model is also verified (accuracy >95%).
科研通智能强力驱动
Strongly Powered by AbleSci AI