Abstract
In many fields of signal processing feed-forward neural networks, especially multilayer perceptron neural networks, are used as approximators. We suggest to state the weight adaptation process (training) as an optimization procedure solving a conventional nonlinear regression problem. Thus the presented theory can easily be adapted to any similar problem.
Recently it has been shown that second order methods yield to a fast decrease of the training error for small and medium scaled neural networks. Especially Marquardt’s algorithm is well known for its simplicity and high robustness.
In this paper we show an innovative approach to minimize the training error. We will demonstrate that an extension of Marquardt’s algorithm, i.e. the adaptation of the increasing/decreasing factor, leads to much better convergence properties than the original formula. Simulation results illustrate excellent robustness concerning the initial values of the weights and less overall computational costs.
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
BATTITI, R. (1992): First and second order methods for learning: Between steepest descent and Newton’s method. Neural Computation, 4(2), pp. 141–166.
CICHOCKI, A. and UNBEHAUEN, R. (1993): Neural networks for optimization and signal processing. Wiley.
DEMUTH, H. and BEALE, M. (1994): Neural network toolbox user’s guide. The MathWorks, Inc.
DENNIS, J. E. and SCHNABEL, R. B. (1996): Numerical methods for unconstrained optimization and nonlinear equations. SIAM.
HAGAN, M. T. and MENHAJ, M. B. (1994): Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5(6), pp. 989–993.
LEVENBERG, K. (1944): A method for the solution of certain problems in least squares. Quart. Appl. Math., 2, pp. 164–168.
LENDL, M., UNBEHAUEN, R. and LUO, L.-F. (1998): A homotopy method for training neural networks. Signal Processing, 6 4(3).
MARQUARDT, D. (1963): An algorithm for least-squares estimation of nonlinear parameters. SIAM J. Appl. Math., 11, pp. 431–441.
OWENS, A. J. and FILKIN, D. L. (1989): Efficient training of the backpropagation network by solving a system of stiff ordinary differential equations. In IJCNN 1989, San Diego, volume 2, pp. 381–386.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin · Heidelberg
About this paper
Cite this paper
Lendl, M., Unbehauen, R. (1999). An Improved Training Method for Feed-Forward Neural Networks. In: Gaul, W., Locarek-Junge, H. (eds) Classification in the Information Age. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60187-3_33
Download citation
DOI: https://doi.org/10.1007/978-3-642-60187-3_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65855-9
Online ISBN: 978-3-642-60187-3
eBook Packages: Springer Book Archive