×

Evolutionary training for dynamical recurrent neural networks: an application in finantial time series prediction. (English) Zbl 1122.68096

Summary: Theoretical and experimental studies have shown that traditional training algorithms for dynamical recurrent neural networks may suffer from 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. 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 financial time series prediction problems.

MSC:

68T05 Learning and adaptive systems in artificial intelligence
91B84 Economic time series analysis
PDFBibTeX XMLCite
Full Text: EuDML