Abstract
In this paper, an alternative fast learning algorithm for supervised neural network was proposed. Both linear multi-regression and back-propagation learning methods were used alternately in the network’s training process. This new learning way is expected to improve the learning efficiency and accuracy of neural network in the real applications. To demonstrate the superiority of the learning method we developed, several examples were simulated. The conventional back-propagation learning method was also performed as the comparison with the new method proposed. From the simulation results shown, the new method we proposed not only has the faster learning speed, but also has the better learning efficiency.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Carpenter, G.A., Grossberg, S.: A Massively Parallel Architecture for a Self-organizing Neural Pattern Recognition Machine. Computer Vision, Graphics, and Image Processing 37, 55–115 (1987)
Chen, S., Billings, S.A., Grant, P.M.: Non-linear System Identification Using Neural Network. International Journal of Control 51, 1191–1214 (1990)
Kaotanzad, A., Hwang, R.C., Abaye, A., Maratukulam, D.: An Adaptive Modular Artificial Neural Network Hourly Load Forecaster and Its Implementation at Electric Utilities. IEEE Trans. On Power System 10, 1716–1722 (1995)
Leonard, J., Kramer, M.A.: Improvement to The Back-propagation Algorithm for Training Neural Network. Computers and Chemical Engineer 14, 337–341 (1986)
Azmi, M.R., Liou, R.: Fast Learning Process of MLPNN Using Recursive Least Squares Methods. IEEE Trans. on Signal Processing 4, 446–450 (1993)
Biegler, F., Omatu, S.: A Learning Algorithm for Multilayer Neural Networks Based on Linear Least Squares Problems. Neural Networks 6, 127–131 (1993)
Verma, B.K., Mulawka, J.J.: Training of The Multiplayer Perceptron Using Direct Solution Methods. In: Proc. 12th IASTED Int. Conf. Appl. Inform., pp. 18–24 (1994)
Mulawka, J.J., Verma, B.K.: Improving The Training Time of the Backpropagation Algorithm. Int. Journal of Microcomputer Application 13, 85–89 (1994)
Verma, B.: Fast Learning of Multilayer Perceptrons. IEEE Trans. on Neural Networks 8, 1314–1320 (1997)
Stager, F., Agarwal, M.: Three Methods to Speed up The Training of Feedforward and Feedback Perceptrons. Neural Networks 10, 1435–1443 (1997)
Xu, C.H., Xu, X.D.: Research of New Learning Method of Feedforward Neural Network. Journal of TSINGHUA University (Science and Technology), 301–307 (1999)
Stubberud, P., Bruce, J.W.: LMS Algorithm for Training Single Layer Globally Recursive Neural Networks. In: IEEE International Conference on Neural Networks - Conference Proceedings, vol. 3, pp. 2214–2217 (1998)
Abid, S., Fnaiech, F., Najim, M.: A Fast Feedforward Training Algorithm Using a Modified Form of The Standard Backpropagation Algorithm. IEEE Trans. on Neural Networks 12, 424–430 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Weng, PH., Huang, CC., Chen, YJ., Huang, HC., Hwang, RC. (2009). An Alternative Fast Learning Algorithm of Neural Network. In: Wang, H., Shen, Y., Huang, T., Zeng, Z. (eds) The Sixth International Symposium on Neural Networks (ISNN 2009). Advances in Intelligent and Soft Computing, vol 56. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01216-7_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-01216-7_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01215-0
Online ISBN: 978-3-642-01216-7
eBook Packages: EngineeringEngineering (R0)