Evolutionary training for Dynamical Recurrent Neural Networks: an application in finantial time series prediction.

• Autores: Miguel Delgado Calvo-Flores, María del Carmen Pegalajar Jiménez, Manuel Pegalajar Cuéllar
• Localización: Mathware & soft computing: The Magazine of the European Society for Fuzzy Logic and Technology, ISSN-e 1134-5632, Vol. 13, Nº. 2, 2006, págs. 89-110
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Theoretical and experimental studies have shown that traditional training algorithms for Dynamical Recurrent Neural Networks may suffer of local optima solutions, due to the error propagation across the recurrence. In the last years, many researchers have put forward different approaches to solve this problem, most of them being based on heuristic procedures. In this paper, the training capabilities of evolutionary techniques are studied, for Dynamical Recurrent Neural Networks. The performance of the models considered is compared in the experimental section, in real finantial time series prediction problems.