A new method to determine the elements of GaAs MESFET from measured S-parameters using neural networks

Author

Gao, Yifan ; Gu, Cong

Author_Institution

Xi´´an Highway Univ., Shaanxi, China

Volume

3

fYear

1999

fDate

1999

Firstpage

904

Abstract

Recently neural networks have been introduced to the microwave area as fast and flexible tools to microwave modeling, simulation and optimization. In this paper, a radial basis transfer function, combined with microwave empirical or semi-analytical information, is proposed. The microwave knowledge complements the capability of learning and generalization of neural networks by providing additional information that may not be adequately represented in a limited set of training data. Such knowledge becomes even more valuable when the neural model is used to extrapolate beyond training data region

Keywords

III-V semiconductors; MESFET circuits; S-parameters; Schottky gate field effect transistors; circuit CAD; gallium arsenide; generalisation (artificial intelligence); learning (artificial intelligence); microwave circuits; microwave field effect transistors; radial basis function networks; semiconductor device models; GaAs; MESFET circuit design; MESFET elements determination; S-parameters; design models; empirical functions; generalization; learning; microwave CAD; microwave knowledge; neural networks; radial basis transfer function; Equivalent circuits; Gallium arsenide; MESFET circuits; Microwave theory and techniques; Neural networks; Neurons; Predictive models; Scattering parameters; Tellurium; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Microwave Conference, 1999 Asia Pacific

Print_ISBN

0-7803-5761-2

Type

conf

DOI

10.1109/APMC.1999.833740

Filename

833740