Title :
Modeling the I-V Curves and Its Derivatives of Microwave Transistors Using Neural Networks
Author :
Landa, Andrés Zárate-de ; Roblin, Patrick ; Reynoso-Hernández, J.A. ; Loo-Yau, J.R.
Author_Institution :
Centro de Investig. Cienc. y Educ. Super. de Ensenada, Ensenada, Mexico
Abstract :
Artificial neural networks are used as a tool in the development of reliable models for field effect transistors. This letter presents an improvement of the classical backpropagation algorithm allowing for the training process information contained in the first derivatives of Ids with respect to the control voltages Vgs and Vds. Excellent agreement between measured and simulated data is achieved up to the third order derivative of Ids .
Keywords :
backpropagation; electronic engineering computing; microwave field effect transistors; neural nets; semiconductor device models; I-V curve modelling; artificial neural networks; backpropagation algorithm; control voltages; microwave field effect transistors; third order derivative; training process information; Artificial neural networks; Biological neural networks; Microwave FETs; Neurons; Training; Artificial neural networks (ANNs); field effect transistor (FET) I-V modeling; training algorithms;
Journal_Title :
Microwave and Wireless Components Letters, IEEE
DOI :
10.1109/LMWC.2012.2210866
