| Título |
Single-step-ahead and multi-step-ahead prediction with evolutionary artificial neural networks |
| Tipo |
Congreso |
| Sub-tipo |
SCOPUS |
| Descripción |
Lecture Notes in Computer Science; 18th Iberoamerican Congress on Pattern Recognition, CIARP 2013 |
| Resumen |
In recent years, Evolutionary Algorithms (EAs) have been remarkably useful to improve the robustness of Artificial Neural Networks (ANNs). This study introduces an experimental analysis using an EAs aimed to evolve ANNs architectures (the FS-EPNet algorithm) to understand how neural networks are evolved with a steady-state algorithm and compare the Single-step-ahead (SSP) and Multiple-step-ahead (MSP) methods for prediction tasks over two test sets. It was decided to test an inside-set during evolution and an outside-set after the whole evolutionary process has been completed to validate the generalization performance with the same method (SSP or MSP). Thus, the networks may not be correctly evaluated (misleading fitness) if the single SSP is used during evolution (inside-set) and then the MSP at the end of it (outside-set). The results show that the same prediction method should be used in both evaluation sets providing smaller errors on average. |
| Observaciones |
(including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics); Code 102325 |
| Lugar |
Havana |
| País |
Cuba |
| No. de páginas |
65-72 |
| Vol. / Cap. |
Vol. 8258, Issue PART 1 |
| Inicio |
2013-11-20 |
| Fin |
2013-11-23 |
| ISBN/ISSN |
978-364241821-1 |
