- Tytuł:
- Chaotic time series prediction with feed-forward and recurrent neural nets
- Autorzy:
-
Mańdziuk, J.
Mikołajczak, R. - Powiązania:
- https://bibliotekanauki.pl/articles/206741.pdf
- Data publikacji:
- 2002
- Wydawca:
- Polska Akademia Nauk. Instytut Badań Systemowych PAN
- Tematy:
-
odwzorowanie logistyczne
predykcja
sieć neuronowa
szereg czasowy chaotyczny
chaotic time series
logistic map
neural networks
prediction - Opis:
- The results of experimental comparison between several neural architectures for short-term chaotic time series prediction problem are presented. Selected feed-forward architectures (Multi-layer Perceptrons) are compared with the most popular recurrent ones (Elman, extended Elman, and Jordan) on the basis prediction accuracy, training time requirements and stability. The application domain is logistic map series - the well known chaotic time series predition benchmark problem. Simulation results suggest that in terms of prediction accuracy feed-forward networks with two hidden layers are superior to other tested architectures. On the other hand feed-forward architectures are, in general, more demanding in terms of training time requirements. Results also indicate that with a careful choice of learning parameters all tested architectures tend to generate stable (repeatable) results.
- Źródło:
-
Control and Cybernetics; 2002, 31, 2; 383-406
0324-8569 - Pojawia się w:
- Control and Cybernetics
- Dostawca treści:
- Biblioteka Nauki
Artykuł