zbMATH — the first resource for mathematics

Functional multi-layer perceptron: A nonlinear tool for functional data analysis. (English) Zbl 1085.68134
Summary: We study a natural extension of Multi-Layer Perceptrons (MLP) to functional inputs. We show that fundamental results for classical MLP can be extended to functional MLP. We obtain universal approximation results that show the expressive power of functional MLP is comparable to that of numerical MLP. We obtain consistency results, which imply that the estimation of optimal parameters for functional MLP is statistically well defined. We finally show on simulated and real world data that the proposed model performs in a very satisfactory way.

68T05 Learning and adaptive systems in artificial intelligence
Full Text: DOI
[1] Abraham, C.; Cornillon, P.-A.; Matzner-Lober, E.; Molinari, N., Unsupervised curve clustering using b-splines, Scandinavian journal of statistics, 30, 3, 581-595, (2003), September · Zbl 1039.91067
[2] Andrews, D.W.K., Consistency in non-linear econometric models: A generic uniform law of large numbers, Econometrica, 55, 6, 1465-1471, (1987), November · Zbl 0646.62101
[3] Besse, P.; Cardot, H., Analyse des données (édité par Gérard govaert), Hermès/lavoisier, ch. 6: modélisation statistique de données fonctionnelles, (2003), pp. 167-198
[4] Besse, P.; Cardot, H.; Faivre, R.; Goulard, M., Statistical modeling of functional data, Applied stochastic models in business and industry, (2004), (in press)
[5] Besse, P.; Cardot, H.; Ferraty, F., Simultaneous non-parametric regressions of unbalanced longitudinal data, Computational statistics and data analysis, 24, 255-270, (1997) · Zbl 0900.62199
[6] Besse, P.; Cardot, H.; Stephenson, D., Autoregressive forecasting of some functional climatic variations, Scandinavian journal of statistics, 4, 673-688, (2000) · Zbl 0962.62089
[7] Breiman, L.; Friedman, J.H.; Olshen, R.A.; Stone, C.J., Classification and regression trees, (1984), Wadsworth Boston, MA · Zbl 0541.62042
[8] Cardot, H.; Ferraty, F.; Sarda, P., Functional linear model, Statistics and probability letters, 45, 11-22, (1999) · Zbl 0962.62081
[9] Cardot, H.; Ferraty, F.; Sarda, P., Spline estimators for the functional linear model, Statistica sinica, 13, 571-591, (2003) · Zbl 1050.62041
[10] Chen, T., A unified approach for neural network-like approximation of non-linear functional, Neural networks, 11, 981-983, (1998)
[11] Chen, T.; Chen, H., Universal approximation to non-linear operators by neural networks with arbitrary activation functions and its application to dynamical systems, IEEE transactions on neural networks, 6, 4, 911-917, (1995), July
[12] Cristianini, N.; Shawe-Taylor, J., An introduction to support vector machines, (2000), Cambridge University Press Cambridge, UK
[13] Ferraty, F.; Goia, A.; Vieu, P., Functional non-parametric model for time series: A fractal approach for dimension reduction, Test, 11, 2, 317-344, (2002), December · Zbl 1020.62089
[14] Ferraty, F.; Vieu, P., The functional non-parametric model and application to spectrometric data, Computational statistics, 17, 4, (2002) · Zbl 1037.62032
[15] Ferraty, F.; Vieu, P., Curves discriminations: A non-parametric functional approach, Computational statistics and data analysis, 44, 1/2, 161-173, (2003) · Zbl 1429.62241
[16] Ferré, L.; Yao, A.-F., Functional sliced inverse regression analysis, Statistics, 37, 6, 475-488, (2003), November/December · Zbl 1032.62052
[17] Hastie, T.; Mallows, C., A discussion of ‘a statistical view of some chemometrics regression tools’ by I.E. Frank and J.H. Friedman, Technometrics, 35, 140-143, (1993)
[18] Hastie, T.; Tibshirani, R.; Friedman, J., The elements of statistical learning: data mining, inference, and prediction, (2001), Springer Berlin · Zbl 0973.62007
[19] Hornik, K., Approximation capabilities of multi-layer feedforward networks, Neural networks, 4, 2, 251-257, (1991)
[20] Hornik, K., Some new results on neural network approximation, Neural networks, 6, 8, 1069-1072, (1993)
[21] James, G.M., Generalized linear models with functional predictor variables, Journal of the royal statistical society series B, 64, 411-432, (2002) · Zbl 1090.62070
[22] James, G.M.; Hastie, T.J., Functional linear discriminant analysis of irregularly sampled curves, Journal of the royal statistical society series B, 63, 533-550, (2001) · Zbl 0989.62036
[23] Leshno, M.; Lin, V.Y.; Pinkus, A.; Schocken, S., Multi-layer feedforward networks with a non-polynomial activation function can approximate any function, Neural networks, 6, 6, 861-867, (1993)
[24] Li, K.-C., Sliced inverse regression for dimension reduction, Journal of the American statistical association, 86, 316-342, (1991) · Zbl 0742.62044
[25] Marx, B.D.; Eilers, P.H., Generalized linear regression on sampled signals with penalized likelihood, ()
[26] Ramsay, J.; Silverman, B., Functional data analysis, Springer series in statistics, (1997), Springer Berlin, June · Zbl 0882.62002
[27] Rudin, W., Real and complex analysis, (1974), McGraw-Hill New York
[28] Sandberg, I.W., Notes on weighted norms and network approximation of functionals, IEEE transactions on circuits and systems—I: fundamental theory and applications, 43, 7, 600-601, (1996), July
[29] Sandberg, I.W.; Xu, L., Network approximation of input – output maps and functionals, Circuits systems signal processing, 15, 6, 711-725, (1996) · Zbl 0876.94055
[30] Stinchcombe, M.B., Neural network approximation of continuous functionals and continuous functions on compactifications, Neural networks, 12, 3, 467-477, (1999)
[31] White, H., Learning in artificial neural networks: A statistical perspective, Neural computation, 1, 4, 425-464, (1989)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.