B. , ]. A. Barron-]-p, and . Bartlett, Universal Approximation Bounds for Superpositions of a Sigmoidal FunctionFor valid generalization, the size of the weights is more important than the size of the network, IEEE Transactions on Information Theory IT-­39 Neural Information Processing Systems, pp.930-945, 1993.

]. G. Cybenko, J. Dreyfus, M. Martinez, and . Samuelides, Approximation by Superpositions of a Sigmoidal Function, Mathematics of Control, Signals and SystemsApprentissage statistique". EYROLLES, Algorithmes, 417 p, pp.303-314, 1989.

]. K. Funahashi, On the approximate realization of continuous mappings by neural networks, Neural Networks, vol.2, issue.3, pp.183-192, 1989.
DOI : 10.1016/0893-6080(89)90003-8

. Gallinari, Practical complexity control in multilayer perceptrons, Signal Processing, vol.74, issue.1, pp.29-46, 1999.
DOI : 10.1016/S0165-1684(98)00200-X

URL : https://hal.archives-ouvertes.fr/hal-01184484

. Geman, Neural Networks and the Bias/Variance Dilemma, Multilayer feedforward networks are universal approximators, pp.1-58, 1989.
DOI : 10.1162/neco.1990.2.1.1

. Hornik, Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks, Neural Networks, vol.3, issue.5, pp.551-560, 1990.
DOI : 10.1016/0893-6080(90)90005-6

]. K. Hornik, Approximation capabilities of multilayer feedforward networks, Neural Networks, vol.4, issue.2, pp.251-257, 1991.
DOI : 10.1016/0893-6080(91)90009-T

. Johannet, Subterranean Water Infiltration Modelling by Neural Networks: Use of Water Source Flow, Proc. of ICANN;? pp1033-­1036. M. Marinaro and P.G. Morasso eds, 1994.

]. D. Mckay, A Practical Bayesian Framework for Backpropagation Networks, Neural Computation, vol.4, issue.3, pp.448-472, 1992.
DOI : 10.1038/323533a0

. Nerrand, Neural Networks and Nonlinear Adaptive Filtering: Unifying Concepts and New Algorithms, Neural Computation, vol.5, issue.2, pp.165-197, 1993.
DOI : 10.1162/neco.1990.2.4.490

. Poggio, Computational vision and regularization theory, Nature, vol.16, issue.6035, pp.314-319, 1985.
DOI : 10.1038/317314a0

]. M. Powell, Radial Basis Functions for Multi-­variable Interpolation : A review IMA Conference on Algorithms for the Approximation of Functions and Data, RMCS Shrivenham, IK, 1985.

. Rumelhart, Learning Internal Representations by error backpropagation". Parallel Distributed Processing : Explorations in the Microstructure of CognitionIll-­conditioning in neural network training problemsNonlinear black-­box modeling in system identification : a unified overviewCross-­validatory choice and assessment of statistical predictionsSolutions of Ill-­Posed Problems, SIAM J. Sci. Stat. Comp. Automatica Journal of the Royal Statistical Society, vol.14, issue.31, pp.318-362, 1974.

]. V. Vapnik, The Nature of Statistical Learning Theory, 1995.

. Yacoub, Une mesure de pertinence pour la sélection de variables dans les perceptrons multicouches ». Revue d'intelligence artificielle, pp.393-410, 2001.

. Zhou, A Systematic and Effective Supervised Learning Mechanism Based on Jacobian Rank Deficiency, Neural Computation, vol.10, issue.4, pp.1031-1045, 1998.
DOI : 10.1109/72.80202

. Coulibaly, Pr??vision hydrologique par r??seaux de neurones artificiels : ??tat de l'art, Canadian Journal of Civil Engineering, vol.26, issue.3, pp.293-304, 1999.
DOI : 10.1139/l98-069

. Coulibaly, A recurrent neural networks approach using indices of low-frequency climatic variability to forecast regional annual runoff, Hydrological Processes, vol.17, issue.15, pp.2755-2777, 2000.
DOI : 10.1002/1099-1085(20001030)14:15<2755::AID-HYP90>3.0.CO;2-9

. Coulibaly, Daily reservoir inflow forecasting using artificial neural networks with stopped training approach, Journal of Hydrology, vol.230, issue.3-4, pp.244-257, 2000.
DOI : 10.1016/S0022-1694(00)00214-6

. Gaume, « Over-­Parametrisation, a major obstacle to the use of artificial neural networks in hydrology ?, Hydrology and Earth System Sciences, pp.693-206, 2003.

. Sahoo, Flow forecasting for a Hawaii stream using rating curves and neural networks, Journal of Hydrology, vol.317, issue.1-2, pp.63-80, 2006.
DOI : 10.1016/j.jhydrol.2005.05.008

. Sahoo, Use of neural network to predict flash flood and attendant water qualities of a mountainous stream on Oahu, Hawaii, Journal of Hydrology, vol.327, issue.3-4, pp.525-538, 2006.
DOI : 10.1016/j.jhydrol.2005.11.059

. Schmitz, PAI-OFF: A new proposal for online flood forecasting in flash flood prone catchments, Journal of Hydrology, vol.360, issue.1-4, pp.1-14, 2008.
DOI : 10.1016/j.jhydrol.2008.07.002

. Zealand, Short term streamflow forecasting using artificial neural networks, Journal of Hydrology, vol.214, issue.1-4, pp.32-48
DOI : 10.1016/S0022-1694(98)00242-X