Neural input space mapping optimization based on nonlinear two-layer perceptrons with optimized nonlinearity
| dc.contributor.author | Gutiérrez-Ayala, Vladimir | |
| dc.contributor.author | Rayas-Sánchez, José E. | |
| dc.date.accessioned | 2013-05-20T18:48:26Z | |
| dc.date.available | 2013-05-20T18:48:26Z | |
| dc.date.issued | 2010-09 | |
| dc.description | 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. | es |
| dc.description.sponsorship | ITESO, A.C. | es |
| dc.description.sponsorship | Intel Guadalajara Design Center | es |
| dc.identifier.citation | 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. | es |
| dc.identifier.issn | 1096-4290 | |
| dc.identifier.uri | http://hdl.handle.net/11117/570 | |
| dc.language.iso | eng | es |
| dc.publisher | Int. J. RF and Microwave CAE | es |
| dc.relation.ispartofseries | Int. J. RF and Microwave CAE;20 | |
| dc.rights.uri | http://quijote.biblio.iteso.mx/licencias/CC-BY-NC-ND-2.5-MX.pdf | es |
| dc.subject | Computer Aided Design (CAD) | es |
| dc.subject | Circuit Design | es |
| dc.subject | Electromagnetic Based Optimization | es |
| dc.subject | Three-Layer Perceptron | es |
| dc.subject | Two-Layer Perceptron | es |
| dc.subject | Microstrip Filters | es |
| dc.subject | Surrogate Modeling | es |
| dc.subject | Neural Space Mapping (NSM) | es |
| dc.subject | Artificial Neural Networks (ANN) | es |
| dc.title | Neural input space mapping optimization based on nonlinear two-layer perceptrons with optimized nonlinearity | es |
| dc.type | info:eu-repo/semantics/article | es |
| rei.peerreviewed | Yes | es |
| rei.revisor | Int. J. RF and Microwave CAE |
Archivos
Bloque original
1 - 1 de 1
No hay miniatura disponible
- Nombre:
- Rayas_10Sep_NSM-2LP.pdf
- Tamaño:
- 1.67 MB
- Formato:
- Adobe Portable Document Format