Bibliographie#
Une approche théorique de l’apprentissage connexionniste, Application à la reconnaissance de la parole, Léon Bottou, Thèse de l’Université de Paris Sud, Centre d’Orsay.
Quasi-Newton methods and their application to function minimization (1967), C. G. Broyden, Math. Comput pages 21-368
Neural networks for pattern recognition (1995), C. M. Bishop, Oxford University Press
Neural modeling for time series: a statistical stepwise methode for weight elimination (1995), M. Cottrel, B. Girard, M. Mangeas, C. Muller, IEEE Transaction On Neural Networks
Approximation by superpositions of a sigmoidal function (1989), G. Cybenko, Mathematics of Controls, Signals, and Systems, p 303-314
Variable metric method for minimization (1959), C. W. Davidon, A.E.C. Research and Development Report, ANL-5990
Optimisation par descente de gradient stochastique de systèmes modulaires combinant réseaux de neurones et programmation dynamique, Application à la reconnaissance de la parole (1996), X. Driancourt, Thèse de l’Université de Paris Sud, Centre d’Orsay.
A rapidly convergent descent method for minimization (1963), R. Fletcher, M. J. D. Powell, Computer Journal 6, pages 163-168
An overview of Unconstrained Optimization (1993), R. Fletcher, Numerical Analysis Report NA/149
On information and sufficiency (1951), S. Kullback, R. A. Leibler, Ann. Math. Stat. 22, pages 79-86
Une procédure d’apprentissage pour réseaux à seuil asymétrique (1985), Yann Le Cun, Cognita, p 599-604
The Levenberg-Marquardt algorithm: Implementation and theory (1977), J. J. Moré, Proceedings of the 1977 Dundee Conference on Numerical Analysis, G. A. Watson, ed., Lecture Notes in Mathematics, vol. 630, Springer-Verlag, Berlin, pages 105-116
Learning internal representations by error propagation (1986), D. E. Rumelhart, G. E. Hinton, R. J. Williams in Parallel distributed processing: explorations in the microstructures of cohniyionn MIT Press, Cambridge
Self-organizing algorithm of robust PCA based on single layer NN (1997) Song Wang, Shaowei Xia, Proceedings of the 4th International Conference Document Analysis and Recognition