人工神经网络
模块化设计
跨导
绝缘体上的硅
计算机科学
MOSFET
电子工程
模块化神经网络
航程(航空)
多层感知器
电压
算法
晶体管
拓扑(电路)
硅
电气工程
人工智能
工程类
材料科学
光电子学
时滞神经网络
操作系统
航空航天工程
作者
Safar Hatami,M.Y. Azizi,H.R. Bahrami,D. Motavalizadeh,Ali Afzali‐Kusha
标识
DOI:10.1109/tcad.2004.836725
摘要
This paper presents neural network (NN) approaches for modeling the I-V characteristics of silicon-on-insulator MOSFETs. The modeling approach is technology independent, fast, and accurate, which makes it suitable for circuit simulators. In the model, two different NN architectures, namely, multilayer perceptron and generalized radial basis function, are used and compared. To increase the training efficiency of the NN, both modular and region partitioning methods have been proposed and utilized. In addition, two approaches for obtaining the transconductance and output conductance of the device are discussed. The first approach makes use of an NN for the conductances, while the second uses the numerical differentiation of the I-V results. To confirm the accuracy of the model, the drain-current characteristics as well as conductances obtained by the model are compared to the simulation data for the points where the NNs are not trained. The comparison shows excellent agreements with relative errors of around 1% over a wide range of drain and gate voltages as well as channel lengths and widths.
科研通智能强力驱动
Strongly Powered by AbleSci AI