\begin{thebibliography}{}

\bibitem[Abramowicz et~al., 1997]{nips-9:Abramowicz+Horn+Naftaly:1997}
Abramowicz, H., Horn, D., Naftaly, U., and Sahar-Pikielny, C. (1997).
\newblock An orientation selective neural network for pattern identification in
  particle detectors.
\newblock In Mozer, M.~C., Jordan, M.~I., and Petsche, T., editors, {\em
  Advances in Neural Information Processing Systems}, volume~9, page 925. The
  {MIT} Press.

\bibitem[Ambroise and Govaert, 1996]{Ambroise}
Ambroise, C. and Govaert, G. (1996).
\newblock Constrained clustering and kohonen self-organizing maps.
\newblock {\em Journal of Classification}, 13(2):299--313.

\bibitem[Anouar et~al., 1998]{Anouar98}
Anouar, F., Badran, F., and Thiria, S. (1998).
\newblock Probabilistic self organizing map and radial basis function.
\newblock {\em Journal of Neurocomputing}, 20:83--96.

\bibitem[Armstrong, 1998]{Goestat98}
Armstrong, M.~A. (1998).
\newblock {\em Basic Linear Geostatistics}.
\newblock Springer-Verlag, New York.

\bibitem[Atteia and Gaches, 1999]{atteiaGaches99}
Atteia, M. and Gaches, J. (1999).
\newblock {\em Approxiation Hilbertienne}.
\newblock Presses Universitaires de Grenoble.

\bibitem[Barron, 1994]{Barron94}
Barron, A.~R. (1994).
\newblock Approximation and estimation bounds for artificial neural networks.
\newblock {\em Machine Learning}, 14:115--133.

\bibitem[Bartlett et~al., 2000]{bouchero00}
Bartlett, P., Boucheron, S., and Lugosi, G. (2000).
\newblock Model selection and error estimation.
\newblock accepted Machine Learning.

\bibitem[Bartlett, 1998]{bartlett98sample}
Bartlett, P.~L. (1998).
\newblock The sample complexity of pattern classification with neural networks:
  the size of the weights is more important than the size of the network.
\newblock {\em IEEE Trans. Inf. Theory}, 44(2):525-- 536.

\bibitem[Bennett and Mangassarian, 1990]{RLP92}
Bennett, K. and Mangassarian, O. (1990).
\newblock Neural networks training via linear programming.
\newblock In Pardalos, P., editor, {\em Advances in Optimization and parallel
  computing}, pages 56--67. North Holland.

\bibitem[Bertels et~al., 2001]{Bertels01}
Bertels, K., Neuberg, L., Vassiliadis, S., and Pechanek, D. (2001).
\newblock On chaos and neural networks: The backpropagation algorithm.
\newblock {\em Artificial Intellignence Review}, 15:165--187.

\bibitem[Birg{\'e} and Massart, 1997]{BirgeMassart97}
Birg{\'e}, L. and Massart, P. (1997).
\newblock From model selection to adaptive estimation.
\newblock In D.~Pollard, E.~T. and Yang, G., editors, {\em Festschrift for
  Lucien Lecam: Research papers in Probability and Statistics}, pages 55--87.

\bibitem[Bishop, 1995]{bishop95}
Bishop, C.~M. (1995).
\newblock {\em Neural Networks for Pattern Recognition}.
\newblock Clarendon Press, Oxford.

\bibitem[Botha et~al., 1996]{nn:Botha+Barnard+Barnard:1996}
Botha, E.~C., Barnard, E., and Barnard, C.~J. (1996).
\newblock Feature-based classification of aerospace radar targets using neural
  networks.
\newblock {\em Neural Networks}, 9(1):129--142.

\bibitem[Bradley et~al., 1999]{DM98}
Bradley, P., Fayyad, U., and Mangassarian, O. (1999).
\newblock Mathematical programmation for data mining: formulation and
  chalanges.
\newblock {\em Journal of computing (special issue on data mining)}.

\bibitem[Bridle, 1990]{BridleNIPS290}
Bridle, J.~S. (1990).
\newblock Training stochastic model recognition algorithms as networks can lead
  to maximum mutual information estimation of parameters.
\newblock In Touretzky, D., editor, {\em Advances in Neural Information
  Processing Systems, NIPS'89}, volume~2, pages 211--217. Morgan-Kaufmann.

\bibitem[Burgess, 1997]{BurgessNips997}
Burgess, A.~N. (1997).
\newblock Estimating equivalent kernels for neural networks: a data
  perturbation approach.
\newblock In Mozer, M.~C., Jordan, M.~I., and Petsche, T., editors, {\em
  Advances in Neural Information Processing Systems}, volume~9, page 382. The
  {MIT} Press.

\bibitem[Campbell, 1997]{campbell97constructive}
Campbell, C. (1997).
\newblock Constructive learning techniques for designing neural network
  systems.
\newblock In Leondes, C., editor, {\em Neural Network Systems Technologies and
  Applications}. Academic Press.

\bibitem[Cesa-Bianchi and Lugosi, 1999]{prediction99}
Cesa-Bianchi, N. and Lugosi, G. (1999).
\newblock On prediction of individual sequences.
\newblock {\em Annals of Statistics}, 27(6).

\bibitem[Chapelle et~al., 2001]{Chapelle01}
Chapelle, O., Weston, J., Bottou, L., and Vapnik, V. (2001).
\newblock Vicinal risk minimization.
\newblock In Leen, T.~K., Dietterich, T.~G., and Tresp, V., editors, {\em
  Advances in Neural Information Processing Systems 13}, pages 416--422. MIT
  Press.

\bibitem[Debnath and Mikusinski, 1998]{gateauDeriv}
Debnath, L. and Mikusinski, P. (1998).
\newblock {\em Introduction to Hilbert Spaces with Applications}.
\newblock Academic Press.

\bibitem[Devroye et~al., 1996]{devroye96probabilistic}
Devroye, L., Gy{\"o}rfi, L., and Lugosi, G. (1996).
\newblock {\em A Probabilistic Theory of Pattern Recognition}.
\newblock Springer, New York.

\bibitem[Dontchev and Zolezzi, 1993]{DontZol93}
Dontchev, A. and Zolezzi, T. (1993).
\newblock {\em Well posed optimization problems}.
\newblock Spinger-Verlag.
\newblock Lecture notes in Mathematics 1543.

\bibitem[Duda et~al., 2001]{nn-books:r.+stork:2001}
Duda, R.~O., Hart, P.~E., and Stork, D.~G. (2001).
\newblock {\em Pattern Classification (2nd ed.)}.
\newblock John Wiley and Sons.
\newblock ISBN: 0-471-05669-3.

\bibitem[Evgeniou et~al., 2000]{EvgPonPog00}
Evgeniou, T., Pontil, M., and Poggio, T. (2000).
\newblock Regularization networks and support vector machines.
\newblock {\em Advances in Computational Mathematics}.

\bibitem[{Fogelman Soulié}, 1997]{Francoise97}
{Fogelman Soulié}, F. (1997).
\newblock réseaux de neurones et statistiques. une introduction.
\newblock In {\em Statistique et méthodes neuronales}. Dunod.

\bibitem[Freund and Schapire, 1999]{freund99short}
Freund, Y. and Schapire, R. (1999).
\newblock A short introduction to boosting.

\bibitem[Friedman, 1997]{Friedman97}
Friedman, J.~H. (1997).
\newblock On bias, variance, 0/1 loss, and the curse of dimensionality.
\newblock {\em Data Mining and Knowledge Discovery}, 1(1):55--77.

\bibitem[Friedman and Stuetzle, 1981]{PPFridman81}
Friedman, J.~H. and Stuetzle, W. (1981).
\newblock Projection pursuit regression.
\newblock {\em Journal of the American Statistical Association}, 76:817--823.

\bibitem[Frie{\ss} et~al., 1998]{FriCriCam98}
Frie{\ss}, T.-T., Cristianini, N., and Campbell., C. (1998).
\newblock The kernel adatron algorithm: {A} fast and simple learning procedure
  for support vector machines.
\newblock In {\em 15th Intl.\ Conf.\ Machine Learning}. Morgan Kaufmann
  Publishers.

\bibitem[Gallinari, 1997]{PatrickGallin97}
Gallinari, P. (1997).
\newblock Méthodes neuronales et discrimination.
\newblock In {\em Statistique et méthodes neuronales}. Dunod.

\bibitem[Gallinari et~al., 1999]{gallinari}
Gallinari, P., Zaragoza, H., and Amini, M.-R. (1999).
\newblock Apprentissage et données textuelles.
\newblock Ecole Modulad - SFdS (Modulad'99).

\bibitem[Ghosh and Nag, 2000]{RBFreviewGhosh90}
Ghosh, J. and Nag, A. (2000).
\newblock Radial basis function networks.
\newblock In Howlett, R.~J. and Jain, L.~C., editors, {\em Radial Basis
  Function Neural Network Theory and Applications}. Physica-Verlag.

\bibitem[Grandvalet et~al., 1997]{Grandvalet97}
Grandvalet, Y., Canu, S., and Boucheron, S. (1997).
\newblock Noise injection: Theoretical prospects.
\newblock {\em Neural Computation}, 9(5):1093--1108.

\bibitem[Hastie and Tibshirani, 1990]{Hastie}
Hastie, T. and Tibshirani, R. (1990).
\newblock {\em Generalized Additive Models}.
\newblock Chapman and Hall.
\newblock Monographs on statistics and applied probability, 43.

\bibitem[Haykin, 1994]{nn-books:Haykin:1994}
Haykin, S. (1994).
\newblock {\em Neural Networks. {A} Comprehensive Foundation}.
\newblock Macmillan College Publishing, New York.

\bibitem[Hertz et~al., 1991]{hertz91}
Hertz, J., Krogh, A., and Palmer, R.~G. (1991).
\newblock {\em An introduction to the theory of Neural Computation}.
\newblock Addison-Wesley.

\bibitem[Hintz-Madsen et~al., 1998]{hintzmadsen98neural}
Hintz-Madsen, M., Hansen, L.~K., Larsen, M. W. P.~J., and Larsen, M. (1998).
\newblock Neural classifier construction using regularization, pruning and test
  error estimation.
\newblock {\em Neural Networks}, 11(9):1659--1670.

\bibitem[Holmst{\"o}m et~al., 1997]{Holmstom97}
Holmst{\"o}m, L., Koistinen, P., Laaksonen, J., and Oja, E. (1997).
\newblock Neural ans statistical classifiers--taxonomy and two case studies.
\newblock {\em IEEE transactions on Neural Networks}, 8(1):5--17.
\newblock {Jain, Alan, Guest editor}.

\bibitem[Hosseini, 2000]{Hosseini00}
Hosseini, S. (2000).
\newblock {\em Contribution à la régression non linéaire par les réseaux de
  neurones}.
\newblock PhD thesis, Institut National Polytechnique de Grenoble.

\bibitem[Jain, 1997]{IEEENNPR}
Jain, A. (1997).
\newblock Special issue on neural network and pattern recognition.
\newblock {\em {IEEE} Transaction on Neural Networks}, 8(1).

\bibitem[Juditsky et~al., 1995]{BBmodelTheorie95}
Juditsky, A., Hjalmarsson, H., Benveniste, A., Delyon, B., Ljung, L., Sjoberg,
  J., and Qinghua, Z. (1995).
\newblock Nonlinear black-box models in system identification: Mathematical
  foundations.
\newblock {\em Automatica}, 31(12):1725--1750.

\bibitem[Kearns et~al., 1997]{MCcompareML97}
Kearns, M., Mansour, Y., Ng, A.~Y., and Ron, D. (1997).
\newblock An experimental and theoretical comparison of model selection
  methods.
\newblock {\em Machine Learning}, 7:7--50.

\bibitem[Kittler, 1986]{Kittler86}
Kittler, J. (1986).
\newblock Feature selection and extraction.
\newblock In {\em Handbook of Pattern Recognition and Image Processing}.
  Accademic Press.

\bibitem[Krauth and Mezard, 1987]{KrauthMezard87}
Krauth, W. and Mezard, M. (1987).
\newblock Learning algorithm with optimal stability in neural networks.
\newblock {\em Journal of Physics A}, 20:745--752.

\bibitem[Lampinen and Vehtari, 2001]{nn:lampinen+vehtari:2001}
Lampinen, J. and Vehtari, A. (2001).
\newblock Bayesian approach for neural networks - review and case studies.
\newblock {\em Neural Networks}, 14(3):257--274.

\bibitem[LeCun et~al., 1998]{effBackProp98}
LeCun, Y., Bottou, L., Orr, G.~B., and M{\"u}ller, K.-R. (1998).
\newblock Efficient backprop.
\newblock In Orr, G.~B. and M{\"u}ller, K.-R., editors, {\em Neural Networks:
  Tricks of the Trade}, pages 5--50. Springer-Verlag, Berlin.
\newblock Springer Lecture Notes in Computer Sciences 1524.

\bibitem[Leray and Gallinari, 2001]{Leray01}
Leray, P. and Gallinari, P. (2001).
\newblock De l'utilisation d'{{\em OBD}} pour la s{\'e}lection de variables
  dans les perceptrons multi-couches.
\newblock {\em Revue d'Intelligence Artificielle}.
\newblock A paraître.

\bibitem[Lodhi et~al., 2001]{LodShaCriWat01}
Lodhi, H., Shawe-Taylor, J., Cristianini, N., and Watkins, C. (2001).
\newblock Text classification using string kernels.
\newblock In Leen, T.~K., Dietterich, T.~G., and Tresp, V., editors, {\em
  Advances in Neural Information Processing Systems 13}, pages 563--569. MIT
  Press.

\bibitem[Makovoz, 1996]{Makovoz96}
Makovoz, Y. (1996).
\newblock Random approximants and neural networks.
\newblock {\em Journal of Approximation Theory}, 85:98--109.

\bibitem[Mangasarian and Musicant, 2001]{ManMus01}
Mangasarian, O.~L. and Musicant, D.~R. (2001).
\newblock Active support vector machine classification.
\newblock In Leen, T.~K., Dietterich, T.~G., and Tresp, V., editors, {\em
  Advances in Neural Information Processing Systems 13}, pages 577--583. MIT
  Press.

\bibitem[Mangassarian, 1993]{Mang93}
Mangassarian, O. (1993).
\newblock Missclassification minimisation.
\newblock {\em Journal of global optimization}, pages 309--323.

\bibitem[Masson and Linster, 1996]{Masson96}
Masson, C. and Linster, C. (1996).
\newblock Towards a cognitive understanding of odor discrimination: combining
  experimental and theoretical approaches.
\newblock {\em Behavioural Processes}, 35:63--82.

\bibitem[Milgram, 1993]{milgram93}
Milgram, M. (1993).
\newblock {\em Reconnaissance des formes : Méthodes numériques et
  connexionnistes}.
\newblock Armand Collin, Paris.

\bibitem[Murata et~al., 1994]{NIC94}
Murata, N., Yoshizawa, S., and Amari, S. (1994).
\newblock Network information criterion -- determining the number of hidden
  units for an artificial neural network model.
\newblock {\em IEEE Transactions on Neural Networks}, 5(6):865--872.

\bibitem[Musavi et~al., 1998]{nn:Musavi+Bryant+Qiao:1998}
Musavi, M., Bryant, R., Qiao, M., Davisson, M., Akeson, E., and French, B.
  (1998).
\newblock Mouse chromosome classification by radial basis function network with
  fast orthogonal search.
\newblock {\em Neural Networks}, 11(4):769--777.

\bibitem[Nadal, 1993]{Nadal93}
Nadal, J. (1993).
\newblock {\em Réseaux de neurones : de la physique à la physiologie}.
\newblock Armand Collin, Paris.

\bibitem[Orr and M{\"u}ller, 1998]{OrrMuller98}
Orr, G.~B. and M{\"u}ller, K.-R. (1998).
\newblock {\em Neural Networks: Tricks of the Trade}.
\newblock Springer-Verlag, Berlin.

\bibitem[Pinkus, 1999]{pinkus99approximation}
Pinkus, A. (1999).
\newblock Approximation theory of the {MLP} model in neural networks.
\newblock {\em Acta Numerica}, 8:143--195.

\bibitem[Poggio and Girosi, 1990]{PoggioGirosi90}
Poggio, T. and Girosi, F. (1990).
\newblock Networks for approximation and learning.
\newblock {\em Proceedings of the IEEE (special issue: Neural Networks I:
  Theory and Modeling)}, 78(9):1481--1497.

\bibitem[Portnoy and Koenker, 1997]{tortoiseHare97}
Portnoy, S. and Koenker, R. (1997).
\newblock The gaussian hare and the laplacian tortoise: Computability of
  squared-error versus absolute error estimates.
\newblock {\em Statistical science}, 12(4):279--300.

\bibitem[Prechelt, 1998]{earlystopping99}
Prechelt, L. (1998).
\newblock Early stopping -- but when?
\newblock In Orr, G.~B. and Muller, K.-R., editors, {\em Neural Networks:
  Tricks of the Trade}, volume 1524, pages 57--69. Springer-Verlag.

\bibitem[Reed, 1993]{pruningRevies93}
Reed, R. (1993).
\newblock Pruning algorithms -- a survey.
\newblock {\em IEEE Transactions on Neural Networks}, 4(5).

\bibitem[Richard and Lengelle, 2001]{RichardLengelle}
Richard, C. and Lengelle, R. (2001).
\newblock Apprentissage de règles de décision à structure imposée et contrôle
  de la complexité.

\bibitem[Ripley, 1996]{Ripley96}
Ripley, B.~D. (1996).
\newblock {\em Pattern recognition and neural networks}.
\newblock Cambridge university press, Cambridge.

\bibitem[{Sch\"olkopf} et~al., 1999]{SchBurSmo99}
{Sch\"olkopf}, B., Burges, C.~J.~C., and Smola, A.~J. (1999).
\newblock {\em Advances in Kernel Methods --- Support Vector Learning}.
\newblock MIT Press, Cambridge, MA.

\bibitem[Sigurdsson et~al., 2000]{revueRgularization00}
Sigurdsson, S., Larsen, J., and Hansen, L. (2000).
\newblock On comparison of adaptive regularization methods.
\newblock In Widrow, B., Guan, L., Paliwa, K., Adali, T., Larsen, J., Wilson,
  E., and Douglas, S., editors, {\em Proceedings of the IEEE Workshop on Neural
  Networks for Signal Processing X}, pages 221--230. IEEE. Sydney.

\bibitem[Smola et~al., 2000]{Smolla2000}
Smola, A.~J., Bartlett, P.~L., Sch{\"o}lkopf, B., and Schuurmans, D., editors
  (2000).
\newblock {\em Advances in Large Margin Classifiers}.
\newblock MIT Press.

\bibitem[Sontag, 1998]{SontagCVdimNN98}
Sontag, E.~D. (1998).
\newblock {VC} dimension of neural networks.
\newblock In Bishop, C., editor, {\em Neural Networks and Machine Learning}.
  Springer-Verlag.

\bibitem[Specht, 1990]{nn:specht90}
Specht, D.~F. (1990).
\newblock Probabilistic neural networks.
\newblock {\em Neural Networks}, 3(1):109--118.

\bibitem[Vapnik, 1995]{nn-books:Vapnik:1995}
Vapnik, V.~N. (1995).
\newblock {\em The nature of statistical learning theory}.
\newblock Springer, New York.

\bibitem[Vapnik, 1999]{nn-books:Vapnik:1999}
Vapnik, V.~N. (1999).
\newblock {\em Statistical learning theory}.
\newblock Wiley inter science.

\bibitem[Waterhouse and Cook, 1997]{nips-9:Waterhouse+Cook:1997}
Waterhouse, S. and Cook, G. (1997).
\newblock Ensemble methods for phoneme classification.
\newblock In Mozer, M.~C., Jordan, M.~I., and Petsche, T., editors, {\em
  Advances in Neural Information Processing Systems}, volume~9, page 800. The
  {MIT} Press.

\bibitem[Weigend et~al., 1998]{nn-books:Weigend+AbuMostafa+Refenes:1998}
Weigend, A.~S., Abu-Mostafa, Y.~S., and Refenes, A.-P.~N., editors (1998).
\newblock {\em Decision Technologies for Financial Engineering: Proceedings of
  the Fourth International Conference on Neural Networks in the Capital Markets
  (NNCM'96)}, volume~7 of {\em Progress in Neural Processing series}.
\newblock World Scientific.

\bibitem[White, 1989]{White89}
White, H. (1989).
\newblock Learning in artificial neural networks: A statistical perspective.
\newblock {\em Neural Computation}, 1:425--464.

\bibitem[Williams and Barber, 1998]{ChrisWillams98}
Williams, C. K.~I. and Barber, D. (1998).
\newblock Bayesian classification with gaussian processes gzipped postscript.
\newblock {\em IEEE Trans Pattern Analysis and Machine Intelligence},
  20(12):1342--1351.

\bibitem[Zhao and Atkeson, 1996]{zhao96implementing}
Zhao, Y. and Atkeson, C.~G. (1996).
\newblock Implementing projection pursuit learning.
\newblock {\em IEEE Transactions on Neural Networks}, 7(2):362--373.

\end{thebibliography}