Mots-clés : machine learning; reproducing kernel; Hilbert space
@article{PMFA_2004_49_3_a4,
author = {K\r{u}rkov\'a, V\v{e}ra},
title = {U\v{c}en{\'\i} neuronov\'ych s{\'\i}t{\'\i} jako inverzn{\'\i} \'uloha},
journal = {Pokroky matematiky, fyziky a astronomie},
pages = {218--225},
year = {2004},
volume = {49},
number = {3},
zbl = {1265.68146},
language = {cs},
url = {http://geodesic.mathdoc.fr/item/PMFA_2004_49_3_a4/}
}
Kůrková, Věra. Učení neuronových sítí jako inverzní úloha. Pokroky matematiky, fyziky a astronomie, Tome 49 (2004) no. 3, pp. 218-225. http://geodesic.mathdoc.fr/item/PMFA_2004_49_3_a4/
[1] Aronszajn, N.: Theory of reproducing kernels. Trans. Amer. Math. Soc. 68 (1950), 33–404. | DOI | MR | Zbl
[2] Berg, C., Christensen, J. P. R., Ressel, P.: Harmonic Analysis on Semigroups. Springer-Verlag, New York 1984. | MR | Zbl
[3] Bertero, M.: Linear inverse and ill-posed problems. Advances in Electronics and Electron Physics 75 (1989), 1–120.
[4] Bjorck, A.: Numerical methods for least squares problem. SIAM 1996. | MR
[5] Cucker, F., Smale, S.: On the mathematical foundations of learning. Bull. Amer. Math. Soc. 39 (2001), 1–49. | DOI | MR
[6] Friedman, A.: Modern Analysis. Dover, New York 1982. | MR | Zbl
[7] Girosi, F.: An equivalence between sparse approximation and support vector machines. Neural Computation 10 (1998), 1455–1480 (AI Memo No 1606, MIT). | DOI
[8] Groetch, C. W.: Generalized Inverses of Linear Operators. Dekker, New York 1977.
[9] Kůrková, V.: High-dimensional approximation by neural networks. Chapter 4 in Advances in Learning Theory: Methods, Models and Applications (J. Stuykens et al., ed.) (2003), 69–88. IOS Press, Amsterdam.
[10] Kůrková, V.: Learning from data as an inverse problem. In Proc. of COMPSTAT 2004 (J. Antoch, ed.), Physica-Verlag, Heidelberg, 1377–1384. | MR
[11] Kůrková, V., Sanguineti, M.: Error estimates for approximate optimization by the extended Ritz method. SIAM J. Optim. (to appear). | MR
[12] Kůrková, V., Sanguineti, M.: Learning with generalization capability by kernel methods with bounded complexity. J. Compl. (to appear). | MR
[13] Moore, E. H.: Abstract. Bulletin AMS 26 (1920), 394–395.
[14] Narcowich, F. J., Sivakumar, N., Ward, J. D.: On condition numbers associated with radial-function interpolation. J. Math. Anal. Appl. 186 (1994), 457–485. | DOI | MR | Zbl
[15] Parzen, E.: An approach to time series analysis. Annals Math. Statistics 32 (1966), 951–989. | DOI | MR
[16] Penrose, R.: A generalized inverse for matrices. Proc. Cambridge Philos. Soc. 52 (1955), 406–413. | MR | Zbl
[17] Poggio, T., Girosi, F.: Networks for approximation and learning. Proc. IEEE 78 (1990), 1481–1497.
[18] Poggio, T., Smale, S.: The mathematics of learning: dealing with data. Notices Amer. Math. Soc. 50 (2003), 536–544. | MR | Zbl
[19] Sejnowski, T. J., Rosenberg, C.: Parallel networks that learn to pronounce English text. Complex Systems 1 (1987), 145–168. | Zbl
[20] Tichonov, A. N., Arsenin, V. Y.: Solutions of Ill-posed Problems. W. H. Winston, Washington, D. C. 1977.
[21] Wahba, G.: Splines Models for Observational Data. SIAM, Philadelphia 1990. | MR
[22] Werbos, P. J.: Backpropagation: Basics and New Developments. The Handbook of Brain Theory and Neural Networks (M. Arbib, ed.), 134–139. MIT Press, Cambridge 1995.