Abstract
In this paper, an improved training algorithm based on the terminal attractor concept for feedforward neural network learning is proposed. A condition to avoid the singularity problem is proposed. The effectiveness of the proposed algorithm is evaluated by various simulation results for a function approximation problem and a stock market index prediction problem. It is shown that the terminal attractor based training algorithm performs consistently in comparison with other existing training algorithms.
Similar content being viewed by others
References
Mehra P., Wah B.W.: Artificial Neural Networks: Concepts and Theory. IEEE Computer Society Press, California (1992)
Zurada J.M.: Introduction to Artificial Neural Systems. West Publishing, St. Paul, MN (1992)
Pardalos, P.M., Resende, M.G.C. (eds): Handbook of Applied Optimization. Oxford University Press, New York (2002)
Pardalos, P.M., Romeijn, E. (ed.): Handbook of Global Optimization, Heuristic Approaches, vol. 2, Kluwer Academic Publishers (2002)
Zhao Y.: On-line neural network learning algorithm with exponential convergence rate. Electronic Lett. 32(15), 1381–1382 (1996)
Zhou G., Si J.: Advanced neural network training algorithm with reduced complexity based on Jacobian deficiency. IEEE Trans. Neural Netw. 9(3), 448–453 (1998)
Parisi R., Di Claudio E.D., Orlandi G., Rao B.D.: A generalized learning paradigm exploiting the structure of feedforward neural networks. IEEE Trans. Neural Netw. 7(6), 1450–1459 (1996)
Hagan M.T., Menhaj M.B.: Training feedforward neural networks with the Marquardt algorithm. IEEE Trans. Neural Netw. 5, 989–993 (1994)
Yu X., Efe O., Kaynak O.: A general backpropagation algorithm for feedforward neural networks learning. IEEE Trans. Neural Netw. 13, 251–259 (2002)
Abid S., Fnaiech F., Najim M.: A fast feedforward training algorithm using a modified form of the standard backpropagation algorithm. IEEE Trans. Neural Netw. 12(2), 424–430 (2001)
Kathirvalavakumar T., Tangavel P.: A modified backpropagation training algorithm for feedforward neural networks. Neural Process. Lett. 23, 11–119 (2006)
Zak M.: Terminal attractors in neural networks. Neural Networks 2, 259–274 (1989)
Wang, S., Hsu, C.H.: Terminal attractor learning algorithms for backpropagation neural networks. In: Proceedings of the International Joint Conference on Neural Networks Singapore, pp. 193–189. IEEE Press (1991)
Bianchi B., Fanelli S., Gori M., Maggini M.: Terminal attractor algorithms: a critical analysis. Neurocomputing 15, 3–13 (1997)
Jiang, M., Yu, X.: Terminal attractor based backpropagation learning for feedforward neural networks. In: Proceedings of the 2001 IEEE International Symposium on Circuits and Systems (ISCAS 2001), pp. 711–714 (2001)
Yu X., Man Z.: Fast terminal sliding-mode control design for nonlinear dynamical systems. IEEE Trans. Circuits Syst. I 49(2), 261–264 (2002)
Demuth, H.B.,Beale, M., Hagan, M.T.:Neural Network Toolbox User’s Guide. The MathWorks Inc (2010)
Azoff E.M.: Neural Network Time Series Forecasting of Financial Markets. John Wiley & Sons, London (1994)
Nenortaite J., Simutis R.: Development and evaluation of decision-making model for stock markets. J. glob. Optim. 36, 1–19 (2006)
Zhang G., Patuwo B.E., Hu M.Y.: Forecasting with artificial neural networks: the state of the art. Int. J. Forecast. 14, 35–62 (1998)
Lachtermacher G., Fuller J.D.: Backpropagation in time-series forecasting. J. Forecast. 14, 381–393 (1995)
Chatfield C.: The Analysis of Time Series: An Introduction. Chapman and Hall, London (2004)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yu, X., Wang, B., Batbayar, B. et al. An improved training algorithm for feedforward neural network learning based on terminal attractors. J Glob Optim 51, 271–284 (2011). https://doi.org/10.1007/s10898-010-9597-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10898-010-9597-6