Abstract
The slow convergence of back-propagation neural network (BPNN) has become a challenge in data-mining and knowledge discovery applications due to the drawbacks of the gradient descent (GD) optimization method, which is widely adopted in BPNN learning. To solve this problem, some standard optimization techniques such as conjugate-gradient and Newton method have been proposed to improve the convergence rate of BP learning algorithm. This paper presents a heuristic method that adds an adaptive smoothing momentum term to original BP learning algorithm to speedup the convergence. In this improved BP learning algorithm, adaptive smoothing technique is used to adjust the momentums of weight updating formula automatically in terms of “3 σ limits theory.” Using the adaptive smoothing momentum terms, the improved BP learning algorithm can make the network training and convergence process faster, and the network’s generalization performance stronger than the standard BP learning algorithm can do. In order to verify the effectiveness of the proposed BP learning algorithm, three typical foreign exchange rates, British pound (GBP), Euro (EUR), and Japanese yen (JPY), are chosen as the forecasting targets for illustration purpose. Experimental results from homogeneous algorithm comparisons reveal that the proposed BP learning algorithm outperforms the other comparable BP algorithms in performance and convergence rate. Furthermore, empirical results from heterogeneous model comparisons also show the effectiveness of the proposed BP learning algorithm.
Similar content being viewed by others
References
Rumelhart D, Hinton G, Williams R. Learning internal representations by error propagation. In: Rumelhart D and McClelland J, eds. Parallel Distributed Processing: Explorations in the Microstructure of Cognition I. Cambridge: MIT Press, 1986, 318–363
Yu L, Wang S Y, Lai K K. A novel nonlinear ensemble forecasting model incorporating GLAR and ANN for foreign exchange rates. Computers & Operations Research, 2005, 32: 2523–2541
Hornik K, Stinchocombe M, White, H. Multilayer feedforward networks are universal approximators. Neural Networksi, 1989, 2: 359–366
White, H. Connectionist nonparametric regression: multilayer feedforward networks can learn arbitrary mappings. Neural Networks, 1990, 3: 535–549
Widrow B, Lehr M A. 30 Years of adaptive neural networks: perception, madaline, and backprpagation. In: Proceedings of the IEEE Neural Networks I: Theory & Modeling, 1990, 1415–1442
Yu X H. Can back-propagation error surface not have local minima? IEEE Transactions on Neural Networks, 1992, 3: 1019–1021
Lawrence S, Giles C L, Tsoi A C. Lessons in neural network training: overfitting may be harder than expected. In: Proceedings of the Fourteenth National Conference on Artificial Intelligence (AAAI-97), California: AAAI Press, 1997, 540–545
Yu L, Wang S Y, Lai K K. An integrated data preparation scheme for neural network data analysis. IEEE Transactions on Knowledge and Data Engineering, 2006, 18(2): 217–230
Yu L, Lai K K, Wang S Y, et al. A bias-variance-complexity trade-off framework for complex system modeling. Lecture Notes in Computer Science, 2006, 3980: 518–527
Ng A Y. Preventing “overfitting” of cross validation data. In: Proceedings of the Fourteenth International Conference on Machine Learning, Nashville: Morgan Kaufmann, 1997, 245–253
Behera L, Kumar S, Patnaik A. On adaptive learning rate that guarantees convergence in Feedforward Networks. IEEE Transactions on Neural Networks, 2006, 17(5): 1116–1125
Chen G, Ogmen H. Modified extended Kalman filtering for supervised learning. International Journal of System Science, 1993, 24: 1207–1214
Iiguni Y, Sakai H, Tokumaru H. A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter. IEEE Transactions on Signal Processing, 1992, 40: 959–966
Ruck D W, Rogers S K, Kabrisky M, et al. Comparative analysis of back-propagation and the extended Kalman filter for training multilayer perceptrons. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14: 686–691
Sha D, Bajic V B. An online hybrid learning algorithm for multilayer perceptron in identification problems. Computers and Electrical Engineering, 2002, 28: 587–598
Zhang Y, Li X R. A fast U-D factorization-based learning algorithm with applications to nonlinear system modeling and identification. IEEE Transactions on Neural Networks, 1999, 10: 930–938
Wang G J, Chen C C. A fast multilayer neural networks training algorithm based on the layer-by-layer optimizing procedures. IEEE Transactions on Neural Networks, 1996, 7: 768–775
Ergezinger S, Thomsen E. An accelerated learning algorithm for multilayer perceptrons: optimization layer by layer. IEEE Transactions on Neural Networks, 1995, 6: 3–42
Allred LG, Kelly GE. Supervised learning techniques for back-propagation networks. In: Proceedings of International Joint Conference on Neural Networks, San Diego, 1990, 1: 702–709
Ooyen A V. Improving the convergence of the back-propagation algorithm. Neural Networks, 1992, 5: 465–571
Shewhart W A. Economic Control of Quality of Manufactured Product. New York: D. Van Nostrand Company, 1931
Yu L, Wang S Y, Lai K K. Adaptive smoothing neural networks in foreign exchange rate forecasting. Lecture Notes in Computer Science, 2005, 3516: 523–530
Yu L, Wang S Y, Lai K K. A novel adaptive learning algorithm for stock market prediction. Lecture Notes in Computer Science, 2005, 3827: 443–452
Yu X H, Chen G A, Cheng S X. Dynamic learning rate optimization of the back propagation algorithm. IEEE Transactions on Neural Networks, 1995, 6(3): 669–677
Chase R B, Quilano A N J, Jacobs R F. Production and Operations Management: Manufacturing and Services. McGraw-Hill, 1998
Raviv Y, Intrator N. Bootstrapping with noise: an effective regularization technique. Connection Science, 1996, 8: 355–372
Yu L, Wang S Y, Lai K K. Foreign-Exchange-Rate Forecasting with Artificial Neural Networks. New York: Springer, 2007
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yu, L., Wang, S. & Lai, K.K. Forecasting foreign exchange rates with an improved back-propagation learning algorithm with adaptive smoothing momentum terms. Front. Comput. Sci. China 3, 167–176 (2009). https://doi.org/10.1007/s11704-009-0020-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11704-009-0020-8