Abstract
In this contribution a new method for supervised training is presented. This method is based on a recently proposed root finding procedure for the numerical solution of systems of non-linear algebraic and/or transcendental equations in IRn. This new method reduces the dimensionality of the problem in such a way that it can lead to an iterative approximate formula for the computation of n−1 connection weights. The remaining connection weight is evaluated separately using the final approximations of the others. This reduced iterative formula generates a sequence of points in IRn−1 which converges quadratically to the proper n−1 connection weights. Moreover, it requires neither a good initial guess for one connection weight nor accurate error function evaluations. The new method is applied on some test cases in order to evaluate its performance. Subject classification: AMS(MOS) 65K10, 49D10, 68T05, 68G05.
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
D. E. Rumelhart and J. L. McClelland eds., Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1, MIT Press, 1986, pp318–362.
R. L. Watrous, Learning algorithms for connectionist networks: applied gradient methods of non-linear optimization, in Proc. IEEE Int. Conf. Neural Networks, San Diego, CA, Vol.2 (1987), pp619–627.
T. N. Grapsa, M. N. Vrahatis, A dimension-reducing method for solving systems of nonlinear equations in IRn, Int. J. Computer Math., Vol.32 (1990), pp 205–216
J. M. Ortega, W. C. Rheinboldt, Iterative Solution of Non-linear Equations in Several Variables, Academic Press, New York, (1970).
J. E. Dennis, R. B. Schnabel, Numerical methods for unconstrained optimization and nonlinear equations, Prentice-Hall, Englewood Cliffs, NJ, (1983).
T. N. Grapsa, M. N. Vrahatis, A dimension-reducing method for unconstrained optimization, J. Comp. Appl. Math. Vol. 66 (1996), pp239–253.
M. N. Vrahatis, Solving systems of non-linear equations using the non zero value of the topological degree, ACM Trans. Math. Software, Vol. 14 (1988), pp312–329.
G. D. Magoulas, M. N. Vrahatis, T. N. Grapsa, G. S. Androulakis, A dimension-reducing training method for feed-forward neural networks, Tech. Rep. CSL-1095, Department of Electrical & Computer Engineering, University of Patras, (1995).
B. J. More, B. S. Garbow, K. E. Hillstrom, Testing unconstrained optimization, ACM Trans. Math. Software, Vol. 7 (1981), pp17–41.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer Science+Business Media New York
About this chapter
Cite this chapter
Magoulas, G.D., Vrahatis, M.N., Grapsa, T.N., Androulakis, G.S. (1997). Neural Network Supervised Training Based on a Dimension Reducing Method. In: Ellacott, S.W., Mason, J.C., Anderson, I.J. (eds) Mathematics of Neural Networks. Operations Research/Computer Science Interfaces Series, vol 8. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-6099-9_41
Download citation
DOI: https://doi.org/10.1007/978-1-4615-6099-9_41
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7794-8
Online ISBN: 978-1-4615-6099-9
eBook Packages: Springer Book Archive