Abstract
An improved compound gradient vector based a fast convergent NN online training weight update scheme is proposed in this paper. The convergent analysis indicates that because the compound gradient vector is employed during the weight update, the convergent speed of the presented algorithm is faster than the back propagation (BP) algorithm. In this scheme an adaptive learning factor is introduced in which the global convergence is obtained, and the convergence procedure on plateau and flat bottom area can speed up. Some simulations have been conducted and the results demonstrate the satisfactory convergent performance and strong robustness are obtained using the improved compound gradient vector NN online learning scheme for real time control involving uncertainty parameter plant.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kuan Chung-Ming, Hornik Kurt: Convergence of Learning Algorithms with Constant Learning Rates. IEEE Transactions on Neural Networks, vol.2 (5, 1991) 484–489
Ngolediage J.E., Naguib R.N.G, Dlay S.S.: Fast Back-Propagation for Supervised Learning. Proceedings of 1993 Internatioanl Joint Conference on Neural Networks, (1993) 2591–2594
Maugoulas G.D., Vrahatis M.N., Androulakis G.S.: Effective Backpropagation Training with variable stepsize, Neural Networks, (1, 1997) 69–82
Van der Smagt P.P.: Minimisation methods for Training Feedforward Neural networks, Neural Networks, (1, 1994) 1–11
Van Ooyen A., Nienhuis B.: Improving the convergence of the Back-Propagation Algorithm, Neural Networks, (3, 1992) 465–471
Zhou G. Si J.: Advanced Neural Networks Training Algorithm with Reduced Complexity based on Jacobian Deficiency, IEEE Transactions on Neural Networks, (3, 1998) 448–453
Hagan M.T., Menhaj M.B.: Training feedforward Neural Networks with the Marquardt Algorithm, IEEE Transactions on Neural Networks, (6, 1994) 989–993
Samad T.: Backpropagation Improvements based Heuristic Arguments, Proceedings of International joint Conference on Neural Networks, (1990) 565–568
Bello M. G.: Enhanced Training Algorithms, and Integrated Training/Architecture Selection for Multilayer Perceptron Networks, IEEE Transactions on Neural networks, (6, 1992) 864–875
Shah S. Palmieri F.: MEKA-A Fast, Local Algorithm for Training Feedforward Neural Networks, Proceedings of international Joint Conference on neural Networks, (1990) 41–46
Parisi R., Di Claudio E. D., Orlandi G., Rao B. D.: A generalized Learning Paradigm Exploiting the Structure of Feedforward Neural Networks, IEEE Transactions on Neural networks, (6, 1996) 1450–1459
Wilamowski Bogdan M., Iqlikci Serdar, Kaynak Okyay, Onder Efe M.: An Algorithm for Fast Convergence in Training Neural Networks, IEEE Proceedings of International Joint Conference on Neural Networks, (2001) 1778–1782
Zaiping Chen, Jun Li, etc., A Neural Network Online Training Algorithm based on Compound Gradient Vector, LNAI, (2002), vol.2457
Xu Lina: Neural Networks Control. Harbin Industrial University Press, Harbin (1999) 123–124
Chen Zaiping, Du Taihang,: Control System Simulations and CAD. Tianjin University Press, Tianjin(2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, Z., Dong, C., Zhou, Q., Zhang, S. (2003). An Improved Compound Gradient Vector Based Neural Network On-Line Training Algorithm. In: Chung, P.W.H., Hinde, C., Ali, M. (eds) Developments in Applied Artificial Intelligence. IEA/AIE 2003. Lecture Notes in Computer Science(), vol 2718. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45034-3_32
Download citation
DOI: https://doi.org/10.1007/3-540-45034-3_32
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40455-2
Online ISBN: 978-3-540-45034-4
eBook Packages: Springer Book Archive