Neural networks vs genetically optimized neural networks in time series prediction - Archive ouverte HAL
Communication Dans Un Congrès Année : 2010

Neural networks vs genetically optimized neural networks in time series prediction

Résumé

This paper deals with methods for finding the suitable weights in an Artificial Neural Network (ANN) using Genetic Algorithms (GA). We study the weakness and strengthness of the proposed approach in case of a statistical data forecasting. We describe a different approach when using the input data during optimization phase. Besides GA, we applied stationary wavelet transform (SWT) as a signal preprocessing, and time-delay neural networks(TDNN) approach for the system’s inputs. Our results show that this optimization is suitable only for certain purposes in case of a statistical data prediction.
Fichier non déposé

Dates et versions

hal-00498317 , version 1 (07-07-2010)

Identifiants

  • HAL Id : hal-00498317 , version 1

Citer

Ion Railean, Sorin Moga, Monica Borda, Cristina Laura Stolojescu. Neural networks vs genetically optimized neural networks in time series prediction. SMTDA2010 : Stochastic Modeling Techniques and Data Analysis International Conference, Jun 2010, Chania, Greece. ⟨hal-00498317⟩
123 Consultations
0 Téléchargements

Partager

More