Title :
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
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;
Conference_Titel :
Microwave Conference, 1999 Asia Pacific
Print_ISBN :
0-7803-5761-2
DOI :
10.1109/APMC.1999.833740
