Title :
Large-signal modeling of HEMT device based on neural network
Author :
Sun, Lingling ; Liao, YiXing ; Zheng, XueFeng ; Cheng, ZhiGang ; Liu, Jun ; Zhou, Lei
Author_Institution :
CAD Center, Hangzhou Inst. of Electron. Eng., China
Abstract :
In this article, a neural network model using Levenberg-Marquart algorithm and hyperbolic tangent activation function is developed to simulate three nonlinear parameters for HEMT device. Compared with BP neural network, this ANN model can accelerate convergence. The example shows that the developed ANN model possesses higher accuracy and good generalization. It can be applied to device modeling efficiently.
Keywords :
high electron mobility transistors; neural nets; semiconductor device models; HEMT device; Levenberg-Marquart algorithm; artificial neural network; hyperbolic tangent activation function; large-signal model; nonlinear parameters; Analytical models; Artificial neural networks; HEMTs; Heterojunction bipolar transistors; Integrated circuit modeling; Microwave devices; Neural networks; Neurons; Solid modeling; Table lookup;
Conference_Titel :
Microwave and Millimeter Wave Technology, 2002. Proceedings. ICMMT 2002. 2002 3rd International Conference on
Print_ISBN :
0-7803-7486-X
DOI :
10.1109/ICMMT.2002.1187843
