Time series prediction by a neural network model based on bi-directional computation style: A study on generalization performance with the computer-generated time series "Data Set D"

Systems and Computers in Japan

Volumn 34, Issue 10, 2003, Pages 64-75

  Wakuya, Hiroshi ^a   Shida, Katsunori ^a  

^a SAGA UNIVERSITY   (Japan)

Author keywords

Bi directional computation style; Bi directional neural network model; Generalization performance; Time series prediction

Indexed keywords

COMPUTATIONAL METHODS; COMPUTER SIMULATION; MATHEMATICAL MODELS; REGRESSION ANALYSIS; TIME SERIES ANALYSIS;

BIDIRECTIONAL NEURAL NETWORK MODEL; TIME SERIES PREDICTION;

NEURAL NETWORKS;

EID: 0041418027     PISSN: 08821666     EISSN: None     Source Type: Journal    
DOI: 10.1002/scj.10264     Document Type: Article

References (15)

1. Gershenfeld NA, Weigend AS. The future of time series. In: Weigend AS, Gershenfeld NA (editors). Time series prediction: Forecasting the future and understanding the past. Addison-Wesley; 1993, p 1-70.
2. Weigend AS, Huberman BA, Rumelhart DE. Predicting the future: A connectionist approach. Int Neural Syst 1990;1:193-209.
3. Wan EA. Time series prediction by using a connectionist network with internal delay lines. In: Weigend AS, Gershenfeld NA (editors). Time series prediction: Forecasting the future and understanding the past. Addison-Wesley; 1993. p 195-217.
4. Mozer MC. Neural net architectures for temporal sequence processing. In: Weigland AS, Gershenfeld NA (editors). Time series prediction: Forecasting the future and understanding the past. Addison-Wesley; 1993, p 243-264.
5. Cholewo T,Zurada JM. Sequential network construction for time series prediction. Proc IEEE Int Joint Conf on Neural Networks, p 2034-2039, Houston, TX, 1997.
6. Wakuya H, Zurada JM. Bi-directional computing architecture for time series prediction. Neural Networks 2001:14:1307-1321.
7. Schuster M, Paliwal KK. Bidirectional recurrent neural networks. IEEE Trans Signal Process 1997;45:2673-2681.
8. Wakuya H, Zurada JM. Time series prediction by a bi-directional computing architecture using future-past information integration: Application to the sunspots number prediction. Tech Rep IEICE 2000;NC99-107.
9. Wakuya H, Zurada JM. Time series prediction by a neural network model based on the bi-directional computation style. Proc IEEE-INNS-ENNS Int Joint Conf on Neural Networks, No. TE3-1, p II-225-230, Como, Italy, 2000.
10. Wakuya H, Shida K, Zurada JM. Bi-directionalization of neural computing architecture for time series prediction: Application to Computer Generated Series 'Data Set D'. Proc 6th Int Conf on Soft Computing, No. C-4-2, p 660-667, Iizuka, Japan, 2000.
11. Wakuya H, Futami R, Hoshimiya N. A bi-directional neural network model for generation and recognition of temporal patterns. IEICE Trans Inf Syst (Jpn Ed) 1994;J77-D-II:236-243.
12. Williams RJ, Zipser D. A learning algorithm for continually running fully recurrent neural networks. Neural Computation 1989;1:270-280.
13. Gaweda AE, Zurada JM. Fuzzy neural network with relational fuzzy rules. Proc IEEE-INNS-ENNS Int Joint Conf on Neural Networks, No. HA1-1, p V-3-7, Como, Italy, 2000.
14. Wakuya H, Shida K, Zurada JM. Bi-directionalization of neural computing architecture for time series prediction. II: Application to Mackey-Glass chaotic time series. Proc Int Conf on Dynamical Aspects in Complex Systems from Cells to Brain, No. PS58, p 43-44, Sendai, Japan, 2000.
15. Wakuya H, Futami R, Hoshimiya N. Development process of temporal pattern transformations in bi-directional neural network models. Tech Rep IEICE 1993;NC93-31.