Previous |  Up |  Next


Title: Učení neuronových sítí jako inverzní úloha (Czech)
Title: Neural nets learning as an inverse problem (English)
Author: Kůrková, Věra
Language: Czech
Journal: Pokroky matematiky, fyziky a astronomie
ISSN: 0032-2423
Volume: 49
Issue: 3
Year: 2004
Pages: 218-225
Category: math
Keyword: machine learning
Keyword: reproducing kernel
Keyword: Hilbert space
MSC: 46E22
MSC: 47B32
MSC: 65J22
MSC: 68T05
MSC: 82N32
idZBL: Zbl 1265.68146
Date available: 2010-12-11T20:37:23Z
Last updated: 2015-11-29
Stable URL:
Reference: [1] Aronszajn, N.: Theory of reproducing kernels.Trans. Amer. Math. Soc. 68 (1950), 33–404. Zbl 0037.20701, MR 0051437, 10.1090/S0002-9947-1950-0051437-7
Reference: [2] Berg, C., Christensen, J. P. R., Ressel, P.: Harmonic Analysis on Semigroups.Springer-Verlag, New York 1984. Zbl 0619.43001, MR 0747302
Reference: [3] Bertero, M.: Linear inverse and ill-posed problems.Advances in Electronics and Electron Physics 75 (1989), 1–120.
Reference: [4] Bjorck, A.: Numerical methods for least squares problem.SIAM 1996. MR 1386889
Reference: [5] Cucker, F., Smale, S.: On the mathematical foundations of learning.Bull. Amer. Math. Soc. 39 (2001), 1–49. MR 1864085, 10.1090/S0273-0979-01-00923-5
Reference: [6] Friedman, A.: Modern Analysis.Dover, New York 1982. Zbl 0557.46001, MR 0663003
Reference: [7] Girosi, F.: An equivalence between sparse approximation and support vector machines.Neural Computation 10 (1998), 1455–1480 (AI Memo No 1606, MIT). 10.1162/089976698300017269
Reference: [8] Groetch, C. W.: Generalized Inverses of Linear Operators.Dekker, New York 1977.
Reference: [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.
Reference: [10] Kůrková, V.: Learning from data as an inverse problem.In Proc. of COMPSTAT 2004 (J. Antoch, ed.), Physica-Verlag, Heidelberg, 1377–1384. MR 2173152
Reference: [11] Kůrková, V., Sanguineti, M.: Error estimates for approximate optimization by the extended Ritz method.SIAM J. Optim. (to appear). MR 2144176
Reference: [12] Kůrková, V., Sanguineti, M.: Learning with generalization capability by kernel methods with bounded complexity.J. Compl. (to appear). MR 2138445
Reference: [13] Moore, E. H.: Abstract.Bulletin AMS 26 (1920), 394–395.
Reference: [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. Zbl 0813.65005, MR 1293005, 10.1006/jmaa.1994.1311
Reference: [15] Parzen, E.: An approach to time series analysis.Annals Math. Statistics 32 (1966), 951–989. MR 0143315, 10.1214/aoms/1177704840
Reference: [16] Penrose, R.: A generalized inverse for matrices.Proc. Cambridge Philos. Soc. 52 (1955), 406–413. Zbl 0065.24603, MR 0069793
Reference: [17] Poggio, T., Girosi, F.: Networks for approximation and learning.Proc. IEEE 78 (1990), 1481–1497.
Reference: [18] Poggio, T., Smale, S.: The mathematics of learning: dealing with data.Notices Amer. Math. Soc. 50 (2003), 536–544. Zbl 1083.68100, MR 1968413
Reference: [19] Sejnowski, T. J., Rosenberg, C.: Parallel networks that learn to pronounce English text.Complex Systems 1 (1987), 145–168. Zbl 0655.68107
Reference: [20] Tichonov, A. N., Arsenin, V. Y.: Solutions of Ill-posed Problems.W. H. Winston, Washington, D. C. 1977.
Reference: [21] Wahba, G.: Splines Models for Observational Data.SIAM, Philadelphia 1990. MR 1045442
Reference: [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.


Files Size Format View
PokrokyMFA_49-2004-3_5.pdf 275.4Kb application/pdf View/Open
Back to standard record
Partner of
EuDML logo