| L. Chudy and I. Farkas, \Prediction of chaotic time-series using dynamic cell structuresand local linear models," Neural Network World, vol. 8, no. 5, pp. 481-489, 1998. |
....time delays t, t 6, t 12 and t 18 or larger was used. Summary of previous approaches: BPNN [11] A BP continuous time feed forward NNs with two hidden layers and with xed time delays. ATNN [11] A BP continuous time feed forward NNs with two hidden layers and with adaptable time delays. DCS LMM [12]: Dynamic Cell Structures combined with Local Linear Models. EBPTTRNN [13] RNNs with 10 adaptive delayed connections trained with BPTT combined with a constructive algorithm. BGALR [14] A genetic algorithm with adaptable input time window size (Breeder Genetic Algorithm with Line Recombination) ....
L. Chudy and I. Farkas, \Prediction of chaotic time-series using dynamic cell structuresand local linear models," Neural Network World, vol. 8, no. 5, pp. 481-489, 1998.
....5 Model Author Description BPNN Day and Davenport (1993) A BP continuous time feed forward NNs with two hidden layers and with xed time delays. ATNN Day and Davenport (1993) A BP continuous time feed forward NNs with two hidden layers and with adaptable time delays. DCS LMM Chudy and Farkas (1998) Dynamic Cell Structures combined with Local Linear Models. EBPTTRNN Bon e, Crucianu, Verley, and Asselin de Beauville (2000) RNNs with 10 adaptive delayed connections trained with BPTT combined with a constructive algorithm. BGALR Falco, Iazzetta, Natale, and Tarantino (1998) A genetic ....
....1.5035 6th order Polynom. Crowder, 1990) 0.04 0.85 BPNN (Lapedes Farber, 1987) 0.02 0.06 FTNN (Day Davenport, 1993) 20 120 7 10 7 0.012 ATNN (Day Davenport, 1993) 20 120 7 10 7 0.005 Cascade Correlation (Crowder, 1990) 20 250 0.04 0. 17 DCS LLM (Chudy Farkas, 1998) 200 200 2 1 10 5 0.0055 0.03 EBPTTRNN (Bon e et al. 2000) 6 65 0.0115 BGALR (Falco et al. 1998) 16 150 0.2373 0.267 EPNet (Yao Liu, 1997) 10 100 1 10 4 0.02 0.06 SOM 10x10 1:5 10 4 0.013 0.06 (Vesanto, 1997) 35x35 1:5 10 4 0.0048 ....
Chudy, L., & Farkas, I. (1998). Prediction of chaotic time-series using dynamic cell structuresand local linear models. Neural Network World, 8 (5), 481-489.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC