P. Amari, O. Amari, S. Park, H. Ozeki, and T. , Singularities affect dynamics of learning in Neuromanifolds Neural computation, pp.1007-1065, 2006.

D. Dacunha-castelle and E. Gassiat, Testing in locally conic models, and application to mixture models, ESAIM: Probability and Statistics, vol.1, pp.285-317, 1997.
DOI : 10.1051/ps:1997111

G. Dacunha-castelle, D. Dacunha-castelle, and E. Gassiat, Testing the order of a model using locally conic parameterization: Population mixtures and stationary ARMA process. The Annals of Statistics, pp.1178-1209, 1999.

P. Doukhan, P. Massart, E. Rio, P. Doukhan, P. Massart et al., Invariance principles for absolutely regular empirical processes, Inst. Henri Poincar (B) Probabilits et Statistiques, pp.31-393, 1995.

F. Fukumizu and K. , A Regularity Condition of the Information Matrix of a Multilayer Perceptron Network, Neural Networks, vol.9, issue.5, pp.871-879, 1996.
DOI : 10.1016/0893-6080(95)00119-0

K. Fukumizu, Likelihood ratio of unidentifiable models and multilayer neural networks The Annals of Statistics, pp.833-851, 2003.

M. Oltanu, J. Rynkiewicz, M. Oltanu, and J. Rynkiewicz, Asymptotic properties of autoregressive regime-switching models, ESAIM Probability and statistics, pp.25-47, 2012.
DOI : 10.1051/ps/2011153

E. Gassiat, Likelihood ratio inequalities with applications to various mixtures. Annales de l'Institut Henri Poincaré, pp.897-906, 2002.

F. Hagiwara, K. Hagiwara, and K. Fukumizu, Relation between weight size and degree of over-fitting in neural network regression, Neural Networks, vol.21, issue.1, pp.48-58, 2008.
DOI : 10.1016/j.neunet.2007.11.001

S. Liu, X. Liu, and Y. Shao, asymptotics for likelihood ratio tests under loss of identifiability The Annals of Statistics, pp.807-832, 2003.

J. Yao, On Least Squares Estimation for Stable Nonlinear AR Processes, Annals of the Institute of Statistical Mathematics, vol.52, issue.2, pp.316-331, 2000.
DOI : 10.1023/A:1004117906532