P. Smolensky, In Parallel Distributed Processing: Volume 1 by D. Rumelhart and J. McLelland 194-281, Ch. 6: Information Processing in Dynamical Systems: Foundations of Harmony Theory, 1986.

R. Salakhutdinov and G. Hinton, Deep Boltzmann machines in proc. of Artificial Intelligence and Statistics, pp.448-455, 2009.

G. E. Hinton, Training Products of Experts by Minimizing Contrastive Divergence, Neural Computation, vol.22, issue.8, p.1771, 2002.
DOI : 10.1162/089976600300015385

G. E. Hinton, A Practical Guide to Training Restricted Boltzmann Machines, pp.599-619, 2012.
DOI : 10.1145/1390156.1390290
URL : http://learning.cs.toronto.edu/%7Ehinton/absps/guideTR.pdf

M. Gabrié, E. W. Tramel, and F. Krzakala, Training restricted Boltzmann machines via the Thouless- Anderson-Palmer free energy in proc, of Proceedings of the 28th International Conference on Neural Information Processing Systems NIPS'15, pp.640-648, 2015.

C. Takahashi and M. Yasuda, Mean-Field Inference in Gaussian Restricted Boltzmann Machine, Journal of the Physical Society of Japan, vol.85, issue.3, p.34001, 2016.
DOI : 10.7566/JPSJ.85.034001
URL : http://arxiv.org/pdf/1512.00927

A. Barra, G. Genovese, P. Sollich, and D. Tantari, Phase diagram of restricted Boltzmann machines and generalized Hopfield networks with arbitrary priors arXiv:1702, p.5882, 2017.

L. Zdeborová and F. Krzakala, Advances in Physics, p.453, 2016.

H. Bourlard and Y. Kamp, Auto-association by multilayer perceptrons and singular value decomposition, Biological Cybernetics, vol.13, issue.4-5, p.291, 1988.
DOI : 10.1109/MASSP.1987.1165576

A. M. Saxe, J. L. Mcclelland, and S. Ganguli, Exact solutions to the nonlinear dynamics of learning in deep linear neural networks arXiv:1312, p.6120, 2014.

E. W. Tramel, M. Gabrié, A. Manoel, F. Caltagirone, and F. Krzakala, A Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines, 2017.

P. C. Hohenberg and M. C. Cross, An introduction to pattern formation in nonequilibrium systems, pp.55-92, 1987.
DOI : 10.1007/3-540-17206-8_3

M. Opper and O. Winther, Adaptive and self-averaging Thouless-Anderson-Palmer mean-field theory for probabilistic modeling, Physical Review E, vol.77, issue.5, p.56131, 2001.
DOI : 10.1103/PhysRevLett.77.4671
URL : http://www.cbs.dtu.dk/winther/opper.adaptive_self.ps.Z

E. Agliari, A. Barra, A. Galluzzi, F. Guerra, and F. Moauro, Multitasking Associative Networks, Physical Review Letters, vol.109, issue.26, pp.268101-268108, 2012.
DOI : 10.1088/0305-4470/36/37/302
URL : http://arxiv.org/pdf/1111.5191