R. Battiti, First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method, Neural Computation, vol.8, issue.3, pp.141-166, 1992.
DOI : 10.1162/neco.1989.1.4.425

L. Behara, M. Gopal, and &. S. Chaudhury, Inversion of RBF networks and applications to adaptive control of nonlinear systems, IEE Proceedings, pp.617-624, 1995.
DOI : 10.1049/ip-cta:19952023

C. Bishop, Neural Networks for Pattern Recognition, 1995.

R. R. Baronbarron93-]-a and . Barron, Étude des Réseaux d'Ondelettes Thèse de Doctorat de l'École Normale Supérieure de Lyon Universal Approximation Bounds for Superpositions of a Sigmoidal FunctionMultivariable Functional Interpolation and Adaptive Networks, IEEE Transactions on Information Theory IT-39, pp.930-945, 1988.

M. Cannon, &. J. Slotinecaprile90-]-b, &. F. Caprile, and . Girosi, Space-Frequency Localized Basis Function Networks for Nonlinear System Estimation and Control A non deterministic minimization algorithm, Chen89] S. Chen, S.A. Billings, W. Luo " Orthogonal Least Squares Methods and Their Application to Non?linear System Identification, pp.293-342, 1990.

S. Chen, A. Billings, C. F. Cowan, and &. M. Grant, Practical identification of NARMAX models using radial basis functions, International Journal of Control, vol.13, issue.6, pp.1327-1350, 1990.
DOI : 10.1007/BF01893414

R. Chentouf and &. C. Jutten, Combining Sigmoids and Radial Basis Functions in Evolutive Neural Architectures, Proceedings of the European Symposium on Artificial Neural Networks (ESANN 96), 1996.

A. Cohen and &. J. Kovacheckevic, Wavelets: the mathematical background, Proceedings of the IEEE, vol.84, issue.4, pp.514-522, 1996.
DOI : 10.1109/5.488697

G. Cybenko, Approximation by Superposition of a Sigmoidal Function Mathematics of control, signals and systems, pp.303-314, 1989.

I. Daubechies, The wavelet transform, time-frequency localization and signal analysis, IEEE Transactions on Information Theory, vol.36, issue.5, pp.961-1005, 1990.
DOI : 10.1109/18.57199

I. Daubechies, Ten Lectures on Wavelets CBMS-NSF regional series in applied mathematics, 1992.

G. Dreyfus and &. Y. Idan, The Canonical Form of Nonlinear Discrete-Time Models, Neural Computation, vol.10, issue.1, pp.133-164, 1998.
DOI : 10.1162/neco.1993.5.2.165

S. Elanayar and &. Y. Shin, Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems, IEEE Transactions on Neural Networks, vol.5, issue.4, pp.594-603, 1994.
DOI : 10.1109/72.298229

J. H. Friedman and &. W. Stuetzle, Projection Pursuit Regression, Journal of the American Statistical Association, vol.4, issue.376, pp.817-823, 1981.
DOI : 10.1080/01621459.1981.10477729

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

F. Girosi, M. Jones, and &. T. Poggio, Regularization Theory and Neural Networks Architectures, Neural Computation, vol.26, issue.3, pp.219-269, 1995.
DOI : 10.1016/0893-6080(90)90004-5

E. J. Hartman and &. J. Kowalski, Layered Neural Networks with Gaussian Hidden Units as Universal Approximations, Neural Computation, vol.1, issue.2, pp.210-215, 1990.
DOI : 10.1162/neco.1989.1.2.281

B. Hassibi and &. D. Stork, Second Order Derivatives for Network Pruning: Optimal Brain Surgeon, Advances in Neural Information Processing Systems, pp.164-172, 1993.

Y. Hirose, K. Yamashita, and &. S. Hijiya, Back-propagation algorithm which varies the number of hidden units, Neural Networks, vol.4, issue.1, pp.61-66, 1991.
DOI : 10.1016/0893-6080(91)90032-Z

K. Hornik, M. Stinchcombe, and &. H. White, Multilayer feedforward networks are universal approximators, Neural Networks, vol.2, issue.5, pp.359-366, 1989.
DOI : 10.1016/0893-6080(89)90020-8

K. Hornik, M. Stinchcombe, H. White, and &. P. Auer, Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives, Neural Computation, vol.6, issue.6, pp.1262-1275, 1994.
DOI : 10.1016/0893-6080(94)90063-9

P. J. Huber, Projection Pursuit, The Annals of Statistics, vol.13, issue.2, pp.435-475, 1985.
DOI : 10.1214/aos/1176349519

J. Hwang, S. Lay, M. Maechler, R. Douglas-martin, and &. J. Schimert, Regression modeling in back-propagation and projection pursuit learning, IEEE Transactions on Neural Networks, vol.5, issue.3, pp.342-353, 1994.
DOI : 10.1109/72.286906

M. I. Jordan, Q. Juditsky, B. Zhang, P. Y. Delyon, &. A. Glorennec et al., The Learning of Representations for Sequential PerformanceWavelets in Identification: wavelets, splines, neurons, fuzzies: how good f o r identificationA New Scheme For Incremental Learning Mutidimensional Wavelet Frames Optimal Brain Damage, Thèse de Doctorat Proceedings of the Neural Information Processing Systems-2, pp.1552-1556, 1985.

M. Lehtokangas, J. Saarinen, K. Kaski, P. Huuhtanenlevenberg44-]-k, . U. Levenberglevin92-]-a et al., Initializing Weights of a Multilayer Perceptron Network by Using t h e Orthogonal Least Squares Algorithm A Method for the Solution of Certain Non?linear Problems in Least Squares Neural Networks in Dynamical Systems System Identification ; Theory for the UserA Theory for Multiresolution Signal Decomposition: The Wavelet TransformAn Algorithm For Least-Squares Estimation of Nonlinear Parameters, Thèse de DoctoratMeyer90] Y. Meyer " Ondelettes et Opérateurs I : Ondelettes. " Editions Hermann, pp.982-999, 1944.

M. Minoux-théorie-et-algorrithmesmukhopa93, ]. S. Mukhopadhyay, &. S. Narendranarendra90-]-k, &. K. Narendra, and . Parthasarathy, Programmation Mathématique Editions DunodFlexNet: A Flexible Neural Network Construction Algorithm Disturbance Rejection in Nonlinear Systems Using Neural NetworksIdentification and Control Of Dynamical Systems Using Neural Networks, Proceedings of the European Symposium on Artificial Neural Networks (ESANN 96), pp.63-72, 1983.

J. C. Nash, Compact Numerical Methods for Computers : Linear Algebra and Function Minimization Adam?Hilger LtdRéseaux de Neurones pour le Filtrage Adaptatif, l'Identification et la Commande de Processus, Thèse de Doctorat de l, 1980.

O. Nerrand, P. Roussel-ragot, L. Personnaz, and &. G. Dreyfus, Neural Networks and Nonlinear Adaptive Filtering: Unifying Concepts and New Algorithms, Neural Computation, vol.5, issue.2, pp.165-199, 1993.
DOI : 10.1162/neco.1990.2.4.490

O. Nerrand, P. Roussel-ragot, D. Urbani, L. Personnaz, and &. G. Dreyfus, Training recurrent neural networks: why and how? An illustration in dynamical process modeling, IEEE Transactions on Neural Networks, vol.5, issue.2, pp.178-184, 1994.
DOI : 10.1109/72.279183

Y. Oussar, I. Rivals, L. Personnaz, and &. G. Dreyfus, Training wavelet networks for nonlinear dynamic input???output modeling, Neurocomputing, vol.20, issue.1-3
DOI : 10.1016/S0925-2312(98)00010-1
URL : https://hal.archives-ouvertes.fr/hal-00797616

J. Park and &. W. Sandberg, Universal Approximation Using Radial-Basis-Function NetworksAnalysis and Synthesis of Feedforward Neural Networks Using Discrete Affine Wavelet Transformations, Neural Computation IEEE Trans. on Neural Networks, vol.3, issue.4 1, pp.246-257, 1991.

M. J. Powellpucar95-]-p, &. M. Pucar, and . Millnert, Radial Basis Functions for Multi?variable Interpolation : A Review IMA Conference on Algorithms for the Approximation of Functions and DataSmooth Hinging Hyperplanes -An Alternative to Neural NetsPruning Algorithms -A Survey, Proceedings of 3rd European Control ConferenceRivals95a] I. Rivals "Modélisation et Commande de Processus par Réseaux de Neurones Thèse de Doctorat de l, pp.1173-1178, 1985.

I. Rivals, L. Personnaz, G. Dreyfus, &. J. Ploixrumelhart86-]-d, J. L. Rumelhart et al., Modélisation, classification et commande par réseaux de neurones : principes fondamentaux, méthodologie de conception et illustrations industrielles Dans : Les réseaux de neurones pour la modélisation et la commande de procédés coordonnateur (Lavoisier Tec et Doc), 1995 [Rivals96] I. Rivals & L. Personnaz "Black Box Modeling With State Neural NetworksGaussian Networks for Direct Adaptive ControlStable Adaptive Control of Robot Manipulators Using Neural Networks, J.P. Corriou In Neural Adaptive Control Technology I, R. Zbikowski and K. J. Hunt eds., World Scientific Parallel Distributed Processing IEEE Transactions on Neural Networks Neural Computation, vol.3, issue.7 4, pp.837-863, 1986.

J. Sjöberg, Q. Zhang, L. Ljung, A. Benveniste, and B. Delyon, Nonlinear Black?Box Modeling in System Identification: a Unified Overview Neural Networks for Control Essays on Control: perspectives in the theory and its applications, Stoppi97] H. Stoppiglia " Méthodes statistiques de sélection de modèles neuronaux; applications financières et bancaires Thèse de Doctorat de l, pp.1691-1724, 1993.

M. Cannon and J. E. Slotine, Space-frequency localized basis function networks for nonlinear system estimation and control, Neurocomputing, vol.9, issue.3, pp.293-342, 1995.
DOI : 10.1016/0925-2312(95)00036-1

G. Cybenko, Approximation by Superpositions of a Sigmoidal Function Mathematics of control, signals and systems, pp.303-314, 1989.

K. Hornik, M. Stinchcombe, H. White, and P. Auer, Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives, Neural Computation, vol.6, issue.6, pp.1262-1275, 1994.
DOI : 10.1016/0893-6080(94)90063-9

M. I. Jordan, The Learning of Representations for Sequential Performance, Doctoral Dissertation, 1985.

A. U. Levin, Neural networks in dynamical systems; a system theoretic approach, 1992.

S. Mallat, A theory for multiresolution signal decomposition: the wavelet representation, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.11, issue.7, pp.674-693, 1989.
DOI : 10.1109/34.192463

K. S. Narendra and K. Parthasarathy, Identification and control of dynamical systems using neural networks, IEEE Transactions on Neural Networks, vol.1, issue.1, pp.4-27, 1990.
DOI : 10.1109/72.80202

O. Nerrand, P. L. Roussel-ragot, G. Personnaz, and . Dreyfus, Neural Networks and Nonlinear Adaptive Filtering: Unifying Concepts and New Algorithms, Neural Computation, vol.5, issue.2, pp.165-199, 1993.
DOI : 10.1162/neco.1990.2.4.490

O. Nerrand, P. Roussel-ragot, D. Urbani, L. Personnaz, and G. Dreyfus, Training recurrent neural networks: why and how? An illustration in dynamical process modeling, IEEE Transactions on Neural Networks, vol.5, issue.2, pp.178-184, 1994.
DOI : 10.1109/72.279183

Y. C. Pati and P. S. Krishnaparasad, Analysis and synthesis of feedforward neural networks using discrete affine wavelet transformations, IEEE Transactions on Neural Networks, vol.4, issue.1, pp.73-85, 1993.
DOI : 10.1109/72.182697

E. Polak, Computational Methods in Optimization: A Unified Approach, 1971.

P. Pucar and M. Millnert, Smooth Hinging Hyperplanes -An Alternative to Neural Nets, Proceedings of 3rd European Control Conference, pp.1173-1178, 1995.

I. Rivals, L. Personnaz, G. Dreyfus, and J. L. Ploix, Modélisation, Classification et Commande par Réseaux de Neurones : Principes Fondamentaux, Méthodologie de Conception et Illustrations Industrielles, Les réseaux de Neurones pour la Modélisation et la Commande de Procédés, pp.1-37, 1995.

I. Rivals and L. Personnaz, BLACK-BOX MODELING WITH STATE-SPACE NEURAL NETWORKS, Neural Adaptive Control Technology I (World Scientific, pp.237-264, 1996.
DOI : 10.1142/9789812830388_0008

D. Urbani, P. L. Roussel-ragot, G. Personnaz, and . Dreyfus, The Selection of Neural Models of Non-linear Dynamical Systems by Statistical Tests, Proceedings of the IEEE Conference on Neural Networks for Signal Processing IV, pp.229-237, 1994.

Q. Zhang, A. Benveniste, and W. Networks, Wavelet networks, IEEE Transactions on Neural Networks, vol.3, issue.6, pp.889-898, 1992.
DOI : 10.1109/72.165591

J. Zhang, G. G. Walter, Y. Miao, and W. N. Wayne-lee, Wavelet neural networks for function learning, Wavelet Neural Networks For Function Learning, pp.1485-1497, 1995.
DOI : 10.1109/78.388860