A. Buhot and M. B. , Cost function and pattern distribution of the Bayesian perceptron, Physics Letters A, vol.228, issue.1-2, pp.73-78, 1997.
DOI : 10.1016/S0375-9601(97)00111-4

A. Buhot, J. Moreno, and M. B. , Gordon Numerical simulations of an optimal algorithm for supervised learning, Proceedings ESANN'97, pp.151-156, 1997.

A. Buhot, J. Moreno, and M. B. , Finite size scaling of the Bayesian perceptron, Physical Review E, vol.55, issue.6, pp.7434-7474, 1997.
DOI : 10.1103/PhysRevE.55.7434

A. Buhot and M. B. , Phase transitions in optimal unsupervised learning, Physical Review E, vol.57, issue.3, pp.3326-3359, 1998.
DOI : 10.1103/PhysRevE.57.3326

A. Buhot and W. , Numerical Solution of Hard-Core Mixtures, Physical Review Letters, vol.80, issue.17, pp.3787-90, 1998.
DOI : 10.1103/PhysRevLett.80.3787

M. B. Gordon and A. , Bayesian learning versus optimal learning, Physica A: Statistical Mechanics and its Applications, vol.257, issue.1-4, pp.85-98, 1998.
DOI : 10.1016/S0378-4371(98)00130-7

A. Buhot and W. , Phase separation in two-dimensional additive mixtures, Physical Review E, vol.59, issue.3, pp.2939-2941, 1999.
DOI : 10.1103/PhysRevE.59.2939

A. Buhot and M. B. , Gordon Statistical mechanics of support vector machines, Proceedings ESANN'99, pp.201-206, 1999.

A. Buhot and M. B. , Gordon Detection of two Gaussion clusters, Proceedings ESANN'99, pp.327-332, 1999.

]. L. Bibliographie1, T. B. Abbott, and . Kepler, Universality in the space of interactions for network models, J. Phys. A: Math. Gen, vol.22, pp.2031-2038, 1989.

J. R. De-almeida and D. J. Thouless, Stability of the Sherrington???Kirkpatrick solution of a spin glass model, J. Phys. A: Math. Gen, vol.11, pp.983-990, 1978.
DOI : 10.1142/9789812799371_0012

D. J. Amit, Modeling Brain Function, 1989.
DOI : 10.1017/CBO9780511623257

D. J. Amit, M. R. Evans, H. Horner, and K. Y. Wong, Retrieval phase diagrams for attractor neural networks with optimal interactions, Journal of Physics A: Mathematical and General, vol.23, issue.14, pp.3361-3381, 1990.
DOI : 10.1088/0305-4470/23/14/032

D. J. Amit, H. Gutfreund, and H. Sompolinsky, Storing Infinite Numbers of Patterns in a Spin-Glass Model of Neural Networks, Physical Review Letters, vol.55, issue.14, pp.1530-1533, 1985.
DOI : 10.1103/PhysRevLett.55.1530

J. K. Anlauf and M. Biehl, The AdaTron: An Adaptive Perceptron Algorithm, Europhysics Letters (EPL), vol.10, issue.7, pp.687-692, 1989.
DOI : 10.1209/0295-5075/10/7/014

E. Barkai, D. Hansel, and I. Kanter, Statistical mechanics of a multilayered neural network, Physical Review Letters, vol.65, issue.18, pp.2312-2315, 1990.
DOI : 10.1103/PhysRevLett.65.2312

E. Barkai, D. Hansel, and H. Sompolinsky, Broken symmetries in multilayered perceptrons, Physical Review A, vol.45, issue.6, pp.4146-4161, 1992.
DOI : 10.1103/PhysRevA.45.4146

N. Barkai, H. S. Seung, and H. Sompolinsky, Scaling laws in learning of classification tasks, Physical Review Letters, vol.70, issue.20, pp.3167-3170, 1993.
DOI : 10.1103/PhysRevLett.70.3167

N. Barkai and H. Sompolinsky, Statistical mechanics of the maximum-likelihood density estimation, Physical Review E, vol.50, issue.3, pp.1766-1769, 1994.
DOI : 10.1103/PhysRevE.50.1766

M. Biehl and A. Mietzner, Statistical Mechanics of Unsupervised Learning, Europhysics Letters (EPL), vol.24, issue.5, pp.421-426, 1993.
DOI : 10.1209/0295-5075/24/5/017

M. Biehl and A. Mietzner, Statistical mechanics of unsupervised structure recognition, Journal of Physics A: Mathematical and General, vol.27, issue.6, pp.1885-1897, 1994.
DOI : 10.1088/0305-4470/27/6/015

M. Biehl and M. Opper, Tilinglike learning in the parity machine, Physical Review A, vol.44, issue.10, pp.6888-6894, 1991.
DOI : 10.1103/PhysRevA.44.6888

C. M. Bishop, Neural Networks for Pattern Recognition, 1995.

A. Blandin, THEORIES VERSUS EXPERIMENTS IN THE SPIN GLASS SYSTEMS, Le Journal de Physique Colloques, vol.39, issue.C6, pp.1499-1516, 1978.
DOI : 10.1051/jphyscol:19786593
URL : https://hal.archives-ouvertes.fr/jpa-00218086

B. E. Boser, I. M. Guyon, and V. N. Vapnik, A training algorithm for optimal margin classifiers, Proceedings of the fifth annual workshop on Computational learning theory , COLT '92, 1992.
DOI : 10.1145/130385.130401

L. Bottou and V. N. Vapnik, Local Learning Algorithms, Neural Computation, vol.2, issue.6, pp.888-900, 1992.
DOI : 10.1162/neco.1989.1.2.281
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.49.8736

M. Bouten, Replica symmetry instability in perceptron models, Journal of Physics A: Mathematical and General, vol.27, issue.17, pp.6021-6023, 1994.
DOI : 10.1088/0305-4470/27/17/033

M. Bouten, L. Reimers, and B. Van-rompaey, Learning in the hypercube: A stepping stone to the binary perceptron, Physical Review E, vol.58, issue.2, pp.2378-2385, 1998.
DOI : 10.1103/PhysRevE.58.2378

M. Bouten, J. Schietse, and C. Van-den-broeck, Gradient descent learning in perceptrons: A review of its possibilities, Physical Review E, vol.52, issue.2, pp.1958-1967, 1995.
DOI : 10.1103/PhysRevE.52.1958

A. Buhot and M. B. Gordon, Cost function and pattern distribution of the Bayesian perceptron, Physics Letters A, vol.228, issue.1-2, pp.73-78, 1997.
DOI : 10.1016/S0375-9601(97)00111-4

A. Buhot and M. B. Gordon, Phase transitions in optimal unsupervised learning, Physical Review E, vol.57, issue.3, pp.3326-3333, 1998.
DOI : 10.1103/PhysRevE.57.3326

A. Buhot and M. B. Gordon, Detection of two gaussian clusters, European Symposium on Artificial Neural Networks, pp.327-332, 1999.

A. Buhot and M. B. Gordon, Statistical Mechanics of Support Vector Machines, European Symposium on Artificial Neural Networks, pp.201-206, 1999.

A. Buhot, J. Moreno, and M. B. Gordon, Finite size scaling of the Bayesian perceptron, Physical Review E, vol.55, issue.6, pp.7434-7440, 1997.
DOI : 10.1103/PhysRevE.55.7434

A. Buhot, J. Moreno, and M. B. Gordon, Numerical simulations of an optimal algorithm for supervised learning, European Symposium on Artificial Neural Networks, pp.151-156, 1997.

C. Cortes and V. N. Vapnik, Support-vector networks, Machine Learning, pp.273-297, 1995.
DOI : 10.1007/BF00994018

T. M. Cover, Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition, IEEE Transactions on Electronic Computers, vol.14, issue.3, pp.326-334, 1965.
DOI : 10.1109/PGEC.1965.264137

B. Derrida, E. Gardner, and A. Zippelius, An Exactly Solvable Asymmetric Neural Network Model, Europhysics Letters (EPL), vol.4, issue.2, pp.167-173, 1987.
DOI : 10.1209/0295-5075/4/2/007

B. Derrida, R. B. Griffiths, and A. Prügel-bennett, Finite-size effects and bounds for perceptron models, Journal of Physics A: Mathematical and General, vol.24, issue.20, pp.4907-4940, 1991.
DOI : 10.1088/0305-4470/24/20/022

R. Dietrich, M. Opper, and H. Sompolinsky, Statistical Mechanics of Support Vector Networks, Physical Review Letters, vol.82, issue.14, pp.2975-2978, 1999.
DOI : 10.1103/PhysRevLett.82.2975

R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis, 1973.

S. F. Edwards and P. W. Anderson, Theory of spin glasses, Journal of Physics F: Metal Physics, vol.5, issue.5, pp.965-974, 1975.
DOI : 10.1088/0305-4608/5/5/017

A. Engel, H. M. Köhler, F. Tschepke, H. Vollmayr, and A. Zippelius, Storage capacity and learning algorithms for two-layer neural networks, Physical Review A, vol.45, issue.10, pp.7590-7609, 1992.
DOI : 10.1103/PhysRevA.45.7590

R. Erichsen and W. K. Theumann, Optimal storage of a neural network model: a replica symmetry-breaking solution, Journal of Physics A: Mathematical and General, vol.26, issue.2, pp.61-68, 1993.
DOI : 10.1088/0305-4470/26/2/007

M. Frean, The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural Networks, Neural Computation, vol.2, issue.2, pp.198-209, 1990.
DOI : 10.1088/0305-4470/22/12/019

S. I. Gallant, Three constructive algorithms for network learning, Proc. 8th Ann, pp.15-17, 1986.

E. Gardner, Maximum Storage Capacity in Neural Networks, Europhysics Letters (EPL), vol.4, issue.4, pp.481-485, 1987.
DOI : 10.1209/0295-5075/4/4/016

E. Gardner, The space of interactions in neural network models, Journal of Physics A: Mathematical and General, vol.21, issue.1, pp.257-270, 1988.
DOI : 10.1088/0305-4470/21/1/030

E. Gardner and B. Derrida, Optimal storage properties of neural network models, Journal of Physics A: Mathematical and General, vol.21, issue.1, pp.271-284, 1988.
DOI : 10.1088/0305-4470/21/1/031

E. Gardner and B. Derrida, Three unfinished works on the optimal storage capacity of networks, Journal of Physics A: Mathematical and General, vol.22, issue.12, pp.1983-1994, 1989.
DOI : 10.1088/0305-4470/22/12/004

F. Gerl and U. Krey, Storage capacity and optimal learning of Potts-model perceptrons by a cavity method, Journal of Physics A: Mathematical and General, vol.27, issue.22, pp.7353-7372, 1994.
DOI : 10.1088/0305-4470/27/22/012

F. Gerl and U. Krey, A Kuhn-Tucker cavity method for generalization with applications to perceptrons with Ising and Potts neurons, Journal of Physics A: Mathematical and General, vol.28, issue.23, pp.6501-6516, 1995.
DOI : 10.1088/0305-4470/28/23/007

F. Gerl and U. Krey, Replica Symmetry Breaking and the Kuhn-Tucker Cavity Method in Simple and Multilayer Perceptrons, Journal de Physique I, vol.7, issue.2, pp.303-327, 1997.
DOI : 10.1051/jp1:1997147
URL : https://hal.archives-ouvertes.fr/jpa-00247330

M. B. Gordon, A convergence theorem for incremental learning with realvalued inputs, ICNN'96, pp.381-386, 1996.

M. B. Gordon and A. Buhot, Bayesian learning versus optimal learning, Physica A: Statistical Mechanics and its Applications, vol.257, issue.1-4, pp.85-98, 1998.
DOI : 10.1016/S0378-4371(98)00130-7

M. B. Gordon and D. R. , Learning with a Temperature-Dependent Algorithm, Europhysics Letters (EPL), vol.29, issue.3, pp.257-262, 1995.
DOI : 10.1209/0295-5075/29/3/012

M. Griniasty and H. Gutfreund, Learning and retrieval in attractor neural networks above saturation, Journal of Physics A: Mathematical and General, vol.24, issue.3, pp.715-734, 1991.
DOI : 10.1088/0305-4470/24/3/030

I. M. Guyon, B. E. Boser, and V. N. Vapnik, Automatic capacity tuning of very large VC-dimension classifiers, Advances in Neural Information Processing Systems, pp.147-155, 1993.

G. Györgyi and P. Reimann, Parisi Phase in a Neuron, Physical Review Letters, vol.79, issue.14, pp.2746-2749, 1997.
DOI : 10.1103/PhysRevLett.79.2746

G. Györgyi, N. Tishby-theumann, W. K. Köberle, and R. , Statistical theory of learning a rule, Neural networks and spin glasses, pp.3-36, 1990.

D. Hansel and H. Sompolinsky, Learning from Examples in a Single-Layer Neural Network, Europhysics Letters (EPL), vol.11, issue.7, pp.687-692, 1990.
DOI : 10.1209/0295-5075/11/7/018

D. O. Hebb, The organization of behavior, 1949.

M. Heerema and W. A. Van-leeuwen, Derivation of Hebb's rule, Journal of Physics A: Mathematical and General, vol.32, issue.2, pp.263-287, 1999.
DOI : 10.1088/0305-4470/32/2/004

D. Herschkowitz and J. Nadal, Unsupervised and supervised clustering: The mutual information between parameters and observations, Advances in Neural Information Processing Systems 11, 1999.

D. Herschkowitz and J. Nadal, Unsupervised and supervised learning:??????Mutual information between parameters and observations, Physical Review E, vol.59, issue.3, pp.3344-3360, 1999.
DOI : 10.1103/PhysRevE.59.3344

J. Hertz, A. Krogh, and R. G. Palmer, Introduction to the theory of neural computation, 1991.

J. J. Hopfield, Neural networks and physical systems with emergent collective computational properties, Proc. Natl. Acad. Sci. USA, pp.2554-2588, 1982.

T. B. Kepler and L. F. Abbott, Domains of attraction in neural networks, Journal de Physique, vol.49, issue.10, pp.1657-1662, 1988.
DOI : 10.1051/jphys:0198800490100165700
URL : https://hal.archives-ouvertes.fr/jpa-00210846

O. Kinouchi, AprendizagemótimaAprendizagemótima em percéptrons a partir de exemplos com ruido, 1996.

O. Kinouchi and N. Caticha, Learning algorithm that gives the Bayes generalization limit for perceptrons, Physical Review E, vol.54, issue.1, pp.54-57, 1996.
DOI : 10.1103/PhysRevE.54.R54

S. Kirkpatrick and D. Sherrington, Infinite-ranged models of spin-glasses, Physical Review B, vol.17, issue.11, pp.4384-4403, 1978.
DOI : 10.1103/PhysRevB.17.4384

H. Köhler, S. Diederich, W. Kinzel, and M. Opper, Learning algorithm for a neural network with binary synapses, Z. Phys. B, vol.78, pp.331-342, 1990.

W. Krauth and M. Mézard, Storage capacity of memory networks with binary couplings, Journal de Physique, vol.50, issue.20, pp.3057-3066, 1989.
DOI : 10.1051/jphys:0198900500200305700
URL : https://hal.archives-ouvertes.fr/jpa-00211124

W. Krauth, M. Mézard, and J. Nadal, Bassins of attraction in a Perceptronlike Neural Network, Complex Systems, vol.2, pp.387-408, 1988.

W. Krauth and M. Opper, Critical storage capacity of the J = ?? 1 neural network, Journal of Physics A: Mathematical and General, vol.22, issue.11, pp.519-523, 1989.
DOI : 10.1088/0305-4470/22/11/012

C. Kwon and J. Oh, Exact asymptotic estimates of the storage capacities of the committee machines with overlapping and non-overlapping receptive fields, European Symposium on Artificial Neural Networks, pp.157-162, 1997.

E. Lootens and C. Van-den-broeck, Analysing Cluster Formation by Replica Method, Europhysics Letters (EPL), vol.30, issue.7, pp.381-386, 1995.
DOI : 10.1209/0295-5075/30/7/001

P. Majer, A. Engel, and A. Zippelius, Perceptrons above saturation, Journal of Physics A: Mathematical and General, vol.26, issue.24, pp.7405-7416, 1993.
DOI : 10.1088/0305-4470/26/24/015

C. Marangi, M. Biehl, and S. A. Solla, Supervised Learning from Clustered Input Examples, Europhysics Letters (EPL), vol.30, issue.2, pp.117-122, 1995.
DOI : 10.1209/0295-5075/30/2/010

M. Marchand, M. Golea, and P. Ruján, A Convergence Theorem for Sequential Learning in Two-Layer Perceptrons, Europhysics Letters (EPL), vol.11, issue.6, pp.487-492, 1989.
DOI : 10.1209/0295-5075/11/6/001

D. Martinez and D. Estève, The Offset Algorithm: Building and Learning Method for Multilayer Neural Networks, Europhysics Letters (EPL), vol.18, issue.2, pp.95-100, 1992.
DOI : 10.1209/0295-5075/18/2/001

N. Mati´cmati´c, I. M. Guyon, J. Denker, and V. N. Vapnik, Writer-adaptation for on-line handwritten character recognition, Second International Conference on Pattern Recognition and Document Analysis, pp.187-191, 1993.

W. S. Mcculloch and W. Pitts, A logical calculus of the ideas immanent in nervous activity, The Bulletin of Mathematical Biophysics, vol.5, issue.4, p.115, 1943.
DOI : 10.1007/BF02478259

R. Meir, Empirical Risk Minimization versus Maximum-Likelihood Estimation: A Case Study, Neural Computation, vol.12, issue.1, pp.144-157, 1995.
DOI : 10.1103/RevModPhys.65.499

R. Meir and J. F. Fontanari, Calculation of learning curves for inconsistent algorithms, Physical Review A, vol.45, issue.12, pp.8874-8884, 1992.
DOI : 10.1103/PhysRevA.45.8874

R. Meir and J. F. Fontanari, Learning from examples in weight-constrained neural networks, Journal of Physics A: Mathematical and General, vol.25, issue.5, pp.1149-1168, 1992.
DOI : 10.1088/0305-4470/25/5/021

S. Mertens and A. Engel, Vapnik-Chervonenkis dimension of neural networks with binary weights, Physical Review E, vol.55, issue.4, pp.4478-4488, 1997.
DOI : 10.1103/PhysRevE.55.4478

M. Mézard and J. Nadal, Learning in feedforward layered networks: the tiling algorithm, Journal of Physics A: Mathematical and General, vol.22, issue.12, pp.2191-2203, 1989.
DOI : 10.1088/0305-4470/22/12/019

M. Mézard, G. Parisi, and M. A. Virasoro, Spin glass theory and beyond, World Scientific, 1987.

M. Mézard and S. Patarnello, On the capacity of feedforward and layered networks, 1989.

G. Milde and S. Kobe, An exact learning algorithm for autoassociative neural networks with binary couplings, Journal of Physics A: Mathematical and General, vol.30, issue.7, pp.2349-2352, 1997.
DOI : 10.1088/0305-4470/30/7/016

G. J. Mitchison and R. M. Durbin, Bounds on the learning capacity of some multi-layer networks, Biological Cybernetics, vol.60, issue.5, p.345, 1989.
DOI : 10.1007/BF00204772

R. Monasson and R. Zecchina, Weight Space Structure and Internal Representations: A Direct Approach to Learning and Generalization in Multilayer Neural Networks, Physical Review Letters, vol.75, issue.12, pp.2432-2435, 1995.
DOI : 10.1103/PhysRevLett.75.2432

R. Monasson and R. Zecchina, Weight Space Structure and Internal Representations: A Direct Approach to Learning and Generalization in Multilayer Neural Networks, Physical Review Letters, vol.76, issue.12, p.2205, 1996.
DOI : 10.1103/PhysRevLett.76.2205.3

J. Nadal, STUDY OF A GROWTH ALGORITHM FOR A FEEDFORWARD NETWORK, International Journal of Neural Systems, vol.01, issue.01, pp.55-59, 1989.
DOI : 10.1142/S0129065789000463

W. Nadler and W. Fink, Finite Size Scaling in Neural Networks, Physical Review Letters, vol.78, issue.3, pp.555-558, 1997.
DOI : 10.1103/PhysRevLett.78.555

E. Oja, Simplified neuron model as a principal component analyzer, Journal of Mathematical Biology, vol.35, issue.3, pp.267-273, 1982.
DOI : 10.1007/BF00275687

E. Oja, NEURAL NETWORKS, PRINCIPAL COMPONENTS, AND SUBSPACES, International Journal of Neural Systems, vol.01, issue.01, pp.61-68, 1989.
DOI : 10.1142/S0129065789000475

M. Opper and D. Haussler, Generalization performance of Bayes optimal classification algorithm for learning a perceptron, Physical Review Letters, vol.66, issue.20, pp.2677-2680, 1991.
DOI : 10.1103/PhysRevLett.66.2677

M. Opper and W. Kinzel, Statistical mechanics of generalisation, Models of Neural Networks III, pp.151-209, 1996.

M. Opper, W. Kinzel, J. Kleinz, and R. Nehl, On the ability of the optimal perceptron to generalise, Journal of Physics A: Mathematical and General, vol.23, issue.11, pp.581-586, 1990.
DOI : 10.1088/0305-4470/23/11/012

G. Parisi, Toward a mean field theory for spin glasses, Physics Letters A, vol.73, issue.3, pp.203-205, 1979.
DOI : 10.1016/0375-9601(79)90708-4

G. Parisi, Magnetic properties of spin glasses in a new mean field theory, Journal of Physics A: Mathematical and General, vol.13, issue.5, pp.1887-1895, 1980.
DOI : 10.1088/0305-4470/13/5/047

G. Parisi, The order parameter for spin glasses: a function on the interval 0-1, Journal of Physics A: Mathematical and General, vol.13, issue.3, pp.1101-1112, 1980.
DOI : 10.1088/0305-4470/13/3/042

G. Parisi, A sequence of approximated solutions to the S-K model for spin glasses, Journal of Physics A: Mathematical and General, vol.13, issue.4, pp.115-121, 1980.
DOI : 10.1088/0305-4470/13/4/009

P. Peretto, An Introduction to the Modeling of Neural Networks (UK), collection aléa-saclay edition, 1992.

B. Raffin and M. B. Gordon, Learning and Generalization with Minimerror, A Temperature-Dependent Learning Algorithm, Neural Computation, vol.1, issue.6, p.1182, 1995.
DOI : 10.1103/RevModPhys.65.499

P. Reimann and C. Van-den-broeck, Learning by examples from a nonuniform distribution, Physical Review E, vol.53, issue.4, pp.3989-3998, 1996.
DOI : 10.1103/PhysRevE.53.3989

P. Reimann, C. Van-den-broeck, and G. J. Bex, A Gaussian scenario for unsupervised learning, Journal of Physics A: Mathematical and General, vol.29, issue.13, pp.3521-3535, 1996.
DOI : 10.1088/0305-4470/29/13/021

K. Rose, E. Gurewitz, and G. C. Fox, Statistical mechanics and phase transitions in clustering, Physical Review Letters, vol.65, issue.8, pp.945-948, 1990.
DOI : 10.1103/PhysRevLett.65.945

F. Rosenblatt, The perceptron: A probabilistic model for information storage and organization in the brain., Psychological Review, vol.65, issue.6, p.386, 1958.
DOI : 10.1037/h0042519

F. Rosenblatt, Principles of Neurodynamics -Perceptrons and the Theory of Brain. Spartan Books, 1961.

P. Ruján and M. Marchand, Learning by activating neurons: A new approach to learning in neural networks, Complex Systems, vol.3, p.229, 1989.

D. E. Rumelhart and J. L. Mcclelland, Parallel Distributed Processing, 1986.

J. Schietse, M. Bouten, and C. Van-den-broeck, Training Binary Perceptrons by Clipping, Europhysics Letters (EPL), vol.32, issue.3, pp.279-284, 1995.
DOI : 10.1209/0295-5075/32/3/015

M. Schröder and R. Urbanczik, Comment on ???Finite Size Scaling in Neural Networks???, Physical Review Letters, vol.80, issue.18, p.4109, 1998.
DOI : 10.1103/PhysRevLett.80.4109

H. S. Seung, H. Sompolinsky, and N. Tishby, Statistical mechanics of learning from examples, Physical Review A, vol.45, issue.8, pp.6056-6091, 1992.
DOI : 10.1103/PhysRevA.45.6056

D. Sherrington and S. Kirkpatrick, Solvable Model of a Spin-Glass, Physical Review Letters, vol.35, issue.26, pp.1792-1796, 1975.
DOI : 10.1103/PhysRevLett.35.1792

J. Simon, La reconnaissance des formesàformesà l'´ epreuve des faits, La Recherche, vol.312, pp.58-62, 1998.

J. A. Sirat and J. Nadal, Neural trees: a new tool for classification, Network: Computation in Neural Systems, vol.1, issue.4, pp.423-438, 1990.
DOI : 10.1088/0954-898X_1_4_003

H. Sompolinsky, N. Tishby, and H. S. Seung, Learning from examples in large neural networks, Physical Review Letters, vol.65, issue.13, pp.1683-1686, 1990.
DOI : 10.1103/PhysRevLett.65.1683

J. Moreno, Apprentissage et généralisation par des réseaux de neurones : ´ etude de nouveaux algorithmes constructifs, 1997.

J. M. Torres, M. B. Moreno, and . Gordon, Efficient adaptive learning for classification tasks with binary units, Neural Computation, vol.10, pp.1007-1030, 1998.

J. M. Torres-moreno, P. Peretto, and M. B. Gordon, An evolutive architecture coupled with optimal perceptron learning for classification, European Symposium on Artificial Neural Networks, pp.365-370, 1995.

R. Urbanczik, Storage capacity of the fully-connected committee machine, Journal of Physics A: Mathematical and General, vol.30, issue.11, pp.387-392, 1997.
DOI : 10.1088/0305-4470/30/11/007

F. Vallet, The Hebb Rule for Learning Linearly Separable Boolean Functions: Learning and Generalization, Europhysics Letters (EPL), vol.8, issue.8, pp.747-751, 1989.
DOI : 10.1209/0295-5075/8/8/007

C. Van-den-broeck and P. Reimann, Unsupervised Learning by Examples: On-line versus Off-line, Physical Review Letters, vol.76, issue.12, pp.2188-2191, 1996.
DOI : 10.1103/PhysRevLett.76.2188

B. Van-rompaey, Precursor networks for training the binary perceptron, European Symposium on Artificial Neural Networks, pp.175-180, 1997.

V. N. Vapnik, The nature of statistical learning theory, 1995.

V. N. Vapnik, Statistical learning theory, 1998.

T. L. Watkin, On optimal neural network learning, Physica A: Statistical Mechanics and its Applications, vol.200, issue.1-4, pp.871-876, 1993.
DOI : 10.1016/0378-4371(93)90569-P

T. L. Watkin and J. Nadal, Optimal unsupervised learning, Journal of Physics A: Mathematical and General, vol.27, issue.6, pp.1899-1915, 1994.
DOI : 10.1088/0305-4470/27/6/016

T. L. Watkin, A. Rau, and M. Biehl, The statistical mechanics of learning a rule, Reviews of Modern Physics, vol.65, issue.2, pp.499-543, 1993.
DOI : 10.1103/RevModPhys.65.499

T. L. Watkin, A. Rau, D. Bollé, and J. Van-mourik, Learning multi-class classification problems, Journal de Physique I, vol.2, issue.2, pp.167-180, 1992.
DOI : 10.1051/jp1:1992131
URL : https://hal.archives-ouvertes.fr/jpa-00246470

A. H. West and D. Saad, The statistical mechanics of constructive algorithms, Journal of Physics A: Mathematical and General, vol.31, issue.45, pp.8977-9021, 1998.
DOI : 10.1088/0305-4470/31/45/002

W. Whyte and D. Sherrington, Replica-symmetry breaking in perceptrons, Journal of Physics A: Mathematical and General, vol.29, issue.12, pp.3063-3073, 1996.
DOI : 10.1088/0305-4470/29/12/014

J. Xiong, C. Kwon, and J. Oh, Storage capacity of a fully-connected parity machine with continuous weights, Journal of Physics A: Mathematical and General, vol.31, issue.34, pp.7043-7049, 1998.
DOI : 10.1088/0305-4470/31/34/007

J. Xiong, J. Oh, and C. Kwon, Weight space structure and the storage capacity of a fully connected committee machine, Physical Review E, vol.56, issue.4, pp.4540-4544, 1997.
DOI : 10.1103/PhysRevE.56.4540

H. Yoon and J. Oh, Learning of higher-order perceptrons with tunable complexities, Journal of Physics A: Mathematical and General, vol.31, issue.38, pp.7771-7784, 1998.
DOI : 10.1088/0305-4470/31/38/012