Neural network structures for EM/microwave modeling

Author

Zhang, Q.J. ; Wang, F. ; Devabhaktuni, V.K.

Author_Institution

Dept. of Electron., Carleton Univ., Ottawa, Ont., Canada

Volume

4

fYear

1999

fDate

11-16 July 1999

Firstpage

2576

Abstract

Neural networks have gained attention as a fast and flexible vehicle to EM/microwave modeling, simulation and optimization. Neural network device/circuit models can be used during EM/microwave design to provide instant answers. The structure of the neural network influences factors such as training data and training time required, and the accuracy that could be achieved. This paper discusses various microwave-oriented neural network structures.

Keywords

circuit CAD; circuit analysis computing; circuit optimisation; circuit simulation; feedforward neural nets; learning (artificial intelligence); microwave circuits; multilayer perceptrons; self-organising feature maps; EM/microwave design; EM/microwave modeling; feedforward neural networks; hierarchical neural network; multilayer perceptron; neural network device/circuit models; neural network structures; optimization; self organizing maps; simulation; training data; training time; Data preprocessing; Neodymium; Neural networks; Neurons; Radial basis function networks; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Antennas and Propagation Society International Symposium, 1999. IEEE

Conference_Location

Orlando, FL, USA

Print_ISBN

0-7803-5639-x

Type

conf

DOI

10.1109/APS.1999.789335

Filename

789335