Neural input space mapping optimization based on nonlinear two-layer perceptrons with optimized nonlinearity
Cargando...
Fecha
2010-09
Autores
Gutiérrez-Ayala, Vladimir
Rayas-Sánchez, José E.
Título de la revista
ISSN de la revista
Título del volumen
Editor
Int. J. RF and Microwave CAE
Resumen
Descripción
A neural space mapping optimization algorithm based on nonlinear two layer perceptrons (2LP) is described in this article. This work is an improved version of the Neural Space-Mapping (NSM) algorithm that uses three layer perceptrons (3LP) to implement a nonlinear input mapping function at each iteration. The new version uses a nonlinear 2LP whose nonlinearity is automatically regulated with classical optimization algorithms. Additionally, the new algorithm uses a different optimization method to train the SM-based neuromodel and a more efficient manner to predict the next iterate. With these improvements, we obtain a more efficient and faster algorithm. To verify the algorithm performance, we design some synthetic circuits, as well as a stopband microstrip filter with quarter-wave resonant opens stubs, a bandpass microstrip filter, and a microstrip notch filter with mitered bends. The last three cases use commercially available full-wave electromagnetic simulators. A rigorous comparison is made with the original NSM algorithm, showing the performance improvement achieved by our proposed new formulation.
Palabras clave
Computer Aided Design (CAD), Circuit Design, Electromagnetic Based Optimization, Three-Layer Perceptron, Two-Layer Perceptron, Microstrip Filters, Surrogate Modeling, Neural Space Mapping (NSM), Artificial Neural Networks (ANN)
Citación
V. Gutiérrez-Ayala and J.E. Rayas-Sánchez, “Neural input space mapping optimization based on nonlinear two-layer perceptrons with optimized nonlinearity,” Int. J. RF and Microwave CAE, vol. 20, pp. 512-526, Sep. 2010.