Prediction of time series by a structural learning of neural networks

Fuzzy Sets and Systems

Volumn 82, Issue 2, 1996, Pages 167-176

  Ishikawa, Masumi ^a   Moriyama, Teppei ^a  

^a KYUSHU INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Learning; Model selection; Neural networks; Prediction; Time series

Indexed keywords

BACKPROPAGATION; COMPUTER SIMULATION; ERRORS; LEARNING SYSTEMS; MATHEMATICAL MODELS; PERFORMANCE; TIME SERIES ANALYSIS;

AN INFORMATION CRITERION; FORGETTING; MEAN PREDICTION ERROR; STRUCTURAL LEARNING; TIME SERIES PREDICTION;

NEURAL NETWORKS;

EID: 0030576749     PISSN: 01650114     EISSN: None     Source Type: Journal    
DOI: 10.1016/0165-0114(95)00253-7     Document Type: Article

References (15)

1. H. Akaike, A new look at the statistical model identification, IEEE Trans. Automatic Control 19 (1974) 716-723.
2. G.E.P. Box and G.M. Jenkins, Time Series Analysis - Forecasting and Control (Holden-Day, San Francisco, CA, 1970).
3. J.L. Elman, Finding structure in time, Cognitive Sci. 14 (1990) 179-211.
4. D.B. Fogel, An information criterion for optimal neural network selection, IEEE Trans. Neural Networks 2-5 (1991) 490-497.
5. M. Ishikawa, A structural learning algorithm with forgetting of link weights, IJCNN, Washington DC (1989) 11-626, also Technical Report, TR-90-7, Electrotechnical Laboratory, Japan (1990).
6. M. Ishikawa, A structural learning algorithm with forgetting of link weights, IJCNN, Washington DC (1989) 11-626, also Technical Report, TR-90-7, Electrotechnical Laboratory, Japan (1990).
7. M. Ishikawa, Structural learning and its applications to rule extraction, Proc. ICNN'94, Orlando, FL (1994) 354-359.
8. M. Ishikawa, Learning of modular structured networks, Artificial Intelligence 75 (1995) 51-62.
9. M.I. Jordan, Serial order - a parallel distributed processing approach, ICS Report 8604, UC San Diego, (1976).
10. J. Kreider and J. Haberl, The great energy prediction shootout - concept and summary of the first building data analysis and prediction competition (1993).
11. T. Kurita, A method to determine the number of hidden units of three layered neural networks by information criteria, The Transactions of Institute of Electronics, Information and Communication Engineers, J73-D-II-11, (1990) 1872-1878 (in Japanese).
12. M.C. Mozer, Neural net architectures for temporal sequence processing, in [13].
13. D.C. Plaut, S.J. Nowlan and G.E. Hinton, Experiments on learning by back propagation, Technical Report CMU-CS-86-126, Carnegie-Mellon Univ (1986).
14. A.S. Weigend and N.A. Gershenfeld, Time Series Prediction: Forecasting the Future and Understanding the Past (Addison-Wesley, Reading, MA, 1994).
15. R.J. Williams and D. Zipser, Gradient-based learning algorithm for recurrent networks, in: Y. Chauvin and D.E. Rumelhart Eds., Back Propagation: Theory, Architectures, and Applications (Erlbaum, London, 1995).