Result Details
Application of neural networks: enhancing efficiency of microwave design
Raida Zbyněk, prof. Dr. Ing., UREL (FEEC)
The paper describes the methodology of the automated creation of neural models of microwave structures. During the creation process, artificial neural networks are trained using the combination of the particle swarm optimization and the quasi-Newton method to avoid critical training problems of the conventional neural nets.
Neural models are required being wideband. In order to meet this requirement, feed-forward neural networks and recurrent ones are used for modelling, and their properties are in detail mutually compared.
In the paper, neural networks are used to approximate behaviour of a planar microwave filter (moment method, Zeland IE3D). In order to evaluate the efficiency of neural modelling, global optimizations are performed using numerical models and neural ones. Both approaches are compared from the viewpoint of CPU-time demands and accuracy. Considering conclusions, methodological recommendations for including neural networks to microwave design are formulated.
Feed-forward neural networks, recurrent neural networks, quasi-Newton methods, particle swarm optimization
@article{BUT43189,
author="Petr {Šmíd} and Zbyněk {Raida}",
title="Application of neural networks: enhancing efficiency of microwave design",
year="2006",
volume="12",
number="1",
pages="9"
}