Title :
Signal and noise neural models of pHEMTs
Author :
MarkoviÇ, Vera ; Marinkovic, Zlatica
Author_Institution :
Fac. of Electron. Eng., Nis Univ., Serbia
Abstract :
Low-noise pHEMT transistors, that have excellent performances at microwave frequencies, can be described by their scattering and noise parameters. In this paper, a pHEMT neural model, based on multilayer perceptron neural networks is proposed. The obtained neural models can predict transistor´s signal and noise performances very efficiently and accurately for a broad range of bias conditions in the operating frequency range.
Keywords :
S-parameters; circuit CAD; microwave power transistors; multilayer perceptrons; power HEMT; semiconductor device models; microwave circuit modeling; multilayer perceptron; neural network; noise parameters; pHENIT transistors; power HEMT; scattering parameters; Circuit noise; Frequency; Microwave transistors; Multilayer perceptrons; Neural networks; Noise figure; PHEMTs; Predictive models; Scattering parameters; Signal to noise ratio;
Conference_Titel :
Neural Network Applications in Electrical Engineering, 2002. NEUREL '02. 2002 6th Seminar on
Print_ISBN :
0-7803-7593-9
DOI :
10.1109/NEUREL.2002.1057995
