Inverse problems in data analysis

• Autorzy: Kurkova V.

Warianty tytułu

PL

Problemy odwrotne w analizie danych

• Języki publikacji: EN

Abstrakty

EN

It is shown that learning from data modelled as minimization of error functionals can be reformulated in terms of inverse problems. This reformulation allows to characterize optimal input-output functions of networks with kernel units.

PL

W artykule tym wykazano, że uczenie na podstawie danych modelowane jako minimalizacja funkcjonałów błędu może być sformułowane jako problem odwrotny. Takie sformułowanie pozwala scharakteryzować optymalne funkcje wejścia/wyjścia sieci z elementami jądrowymi.

Słowa kluczowe

EN

learning from data; inverse problem; regularization; reproducing kernel Hilbert spaces

PL

uczenie na podstawie danych; problem odwrotny; regularyzacja; przestrzenie Hilberta; reprodukcja jądra

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2006
• Tom: R. 82, nr 4
• Strony: 41--48
• Opis fizyczny: Bibliogr. 33 poz.

Twórcy

autor

Kurkova V.

• Academy of Sciences of the Czech Republic,

Bibliografia

• [1] Aizerman M. A., Braverman E. M., Rozonoer L. I. (1964). Theoretical foundations of potential function method in pattern recognition learning. Automation and Remote Control 28, 821-837.
• [2] Aronszajn N. (1950). Theory of reproducing kernels. Transactions of AMS 68, 33-404.
• [3] Bertero M. (1989). Linear inverse and ill-posed problems. Advances in Electronics and Electron Physics 75, 1 120.
• [4] Bjorck A. (1996). Numerical Methods for Least Squares Problem. SIAM.
• [5] Boser B., Guyou I., Vapnik V. N. (1992). A training algorithm for optimal margin clasifiers. In Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory (Ed. D. Haussler) (pp. 144-152). ACM Press.
• [6] Cortes C., Vapnik V. N. (1995). Support-vector networks. Machine Learning 20. 273-297.
• [7] Cristianini N., Shawe-Taylor J. (2000). An Introduction to Support Vector Machines. Cambridge: Cambridge University Press.
• [8] Cucker F., Smale S. (2001). On the mathematical foundations of learning. Bulletin of the AMS 39, 1-49.
• [9] De Vito E., Rosasco L., Caponnetto A., De Giovannini U., Odone F. (2005). Learning from examples as an inverse problem. Journal of Machine Learning Research 6, 883-904.
• [10] Dounford N, Schwartz J. T. (1963). Linear Operators. Part II: Spectral Theory. New York: Interscience Publishers.
• [11] Engl H.W., Hanke M., Neubauer A. (2000). Regularization of Inverse Problems. Dordrecht: Kluwer.
• [12] Friedman A. (1982). Modern Analysis. New York: Dover.
• [13] Girosi F. (1998). An equivalence between sparse approximation and support vector machines. Neural Computation 10, 1455-1480 (AI Memo No 1606, MIT).
• [14] Girosi F., Jones M., Poggio T. (1995). Regularization theory and neural network architectures. Neural Computation 7, 219-269.
• [15] Groetch C. W. (1977). Generalized Inverses of Linear Operators. Dekker: New York.
• [16] Hansen P. C. (1998). Rank-Deficient and Discrete III-Posed Problems. Philadelphia: SIAM.
• [17] Kurkova V. (2004). Supervised learning as an inverse problem. Research Report ICS-2004-960, Institute of Computer Science, Prague.
• [18] Kurkova V. (2004). Learning from data as an inverse problem. In COMPSTAT 2004 - Proceedings on Computational Statistics (J. Antoch, Ed.), 1377-1384. Heidelberg: Physica-Verlag/Springer.
• [19] Kurkova V. (2005). Neural network learning as an inverse problem. Logic Journal of IGPL 13, 551-559.
• [20] Kurkova V., Sanguineti M. (2005). Error estimates for approximate optimization by the extended Ritz method. SIAM Journal on Optimization 15, 461-487.
• [21] Kurkova V., Sanguineti M. (2005). Learning with generalization capability by kernel methods with bounded complexity. Journal of Complexity 13, 551-559.
• [22] Moore E. H. (1920). Abstract. Bull. Amer. Math. Soc. 26, 394-395.
• [23] Parzen E. (1966). An approach to time series' analysis. Annals of Math. Statistics 32, 951-989.
• [24] Penrose R. (1955). A generalized inverse for matrices. Proc. Cambridge Philos. Soc. 51, 406-413.
• [25] Pinkus A. (1985). n- Width in Approximation Theory. Berlin: Springer-Verlag.
• [26] Poggio T., Girosi F. (1990). Networks for approximation and learning. Proceedings IEEE 78, 1481 - 1497.
• [27] Poggio T., Smale S. (2003). The mathematics of learning: dealing with data. Notices of the AMS 50, 536-544.
• [28] Popper K. (1968). The Logic of Scientific Discovery. New York: Harper Torch Book.
• [29] Scholkopf B., Smola A. J. (2002). Learning with Kernels - Support Vector Machines, Regularization, Optimization and Beyond. Cambridge: MIT Press.
• [30] Tikhonov A. N., Arsenin V. Y. (1977). Solutions of III-posed Problems. Washington, D.C.: W.H. Winston.
• [31] Vapnik V. N. (1995). The Nature of Statistical Learning Theory. New York: Springer-Verlag.
• [32] Wahba G. (1990). Splines Models for Observational Data. Philadelphia: SIAM.
• [33] Werbos P. J. (1995). Backpropagation: Basics and New Developments. In The Handbook of Brain Theory and Neural Networks (Ed. Arbib M.) (pp. 134-139). Cambridge: MIT Press.