{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T11:30:56Z","timestamp":1791286256445,"version":"4.1.0"},"reference-count":50,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2015,7,6]],"date-time":"2015-07-06T00:00:00Z","timestamp":1436140800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>We study the asymptotic law of a network of interacting neurons when the number of neurons becomes infinite. Given a completely connected network of neurons in which the synaptic weights are Gaussian correlated random variables, we describe the asymptotic law of the network when the number of neurons goes to infinity. We introduce the process-level empirical measure of the trajectories of the solutions to the equations of the finite network of neurons and the averaged law (with respect to the synaptic weights) of the trajectories of the solutions to the equations of the network of neurons. The main result of this article is that the image law through the empirical measure satisfies a large deviation principle with a good rate function which is shown to have a unique global minimum. Our analysis of the rate function allows us also to characterize the limit measure as the image of a stationary Gaussian measure defined on a transformed set of trajectories.<\/jats:p>","DOI":"10.3390\/e17074701","type":"journal-article","created":{"date-parts":[[2015,7,6]],"date-time":"2015-07-06T12:21:05Z","timestamp":1436185265000},"page":"4701-4743","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Asymptotic Description of Neural Networks with Correlated Synaptic Weights"],"prefix":"10.3390","volume":"17","author":[{"given":"Olivier","family":"Faugeras","sequence":"first","affiliation":[{"name":"INRIA Sophia Antipolis Mediterannee, 2004 Route Des Lucioles, Sophia Antipolis, 06410, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"MacLaurin","sequence":"additional","affiliation":[{"name":"INRIA Sophia Antipolis Mediterannee, 2004 Route Des Lucioles, Sophia Antipolis, 06410, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2015,7,6]]},"reference":[{"key":"ref_1","unstructured":"Guionnet, A. (1995). Dynamique de Langevin d\u2019un verre de spins. [Ph.D. Thesis, Universit\u00e9 de Paris Sud]."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1007\/BF01198846","article-title":"Large deviations for Langevin spin glass dynamics","volume":"102","author":"Guionnet","year":"1995","journal-title":"Probab. Theory Relat. Fields."},{"key":"ref_3","first-page":"1367","article-title":"Symmetric Langevin Spin Glass Dynamics","volume":"25","author":"Guionnet","year":"1997","journal-title":"Ann. Probab."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1007\/s004400050130","article-title":"Averaged and quenched propagation of chaos for spin glass dynamics","volume":"109","author":"Guionnet","year":"1997","journal-title":"Probab. Theory Relat. Fields."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1103\/PhysRevLett.47.359","article-title":"Dynamic theory of the spin-glass phase","volume":"47","author":"Sompolinsky","year":"1981","journal-title":"Phys. Rev. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"6860","DOI":"10.1103\/PhysRevB.25.6860","article-title":"Relaxational dynamics of the Edwards-Anderson model and the mean-field theory of spin-glasses","volume":"25","author":"Sompolinsky","year":"1982","journal-title":"Phys. Rev. B"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4922","DOI":"10.1103\/PhysRevA.36.4922","article-title":"Dynamics of spin systems with randomly asymmetric bonds: Langevin dynamics and a spherical model","volume":"36","author":"Crisanti","year":"1987","journal-title":"Phys. Rev. A"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4865","DOI":"10.1103\/PhysRevA.37.4865","article-title":"Dynamics of spin systems with randomly asymmetric bounds: Ising spins and Glauber dynamics","volume":"37","author":"Crisanti","year":"1987","journal-title":"Phys. Rev. A"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1080\/17442508708833446","article-title":"Large deviations from the mckean-vlasov limit for weakly interacting diffusions","volume":"20","author":"Dawson","year":"1987","journal-title":"Stochastics"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1007\/BF01192835","article-title":"Multilevel large deviations and interacting diffusions","volume":"98","author":"Dawson","year":"1994","journal-title":"Probab. Theory Relat. Fields."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1214\/10-AOP616","article-title":"Large deviation properties of weakly interacting processes via weak convergence methods","volume":"40","author":"Budhiraja","year":"2012","journal-title":"Ann. Probab."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.3150\/13-BEJ540","article-title":"On the form of the large deviation rate function for the empirical measures of weakly interacting systems","volume":"20","author":"Fischer","year":"2014","journal-title":"Bernoulli"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1103\/PhysRevLett.61.259","article-title":"Chaos in Random Neural Networks","volume":"61","author":"Sompolinsky","year":"1988","journal-title":"Phys. Rev. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Gerstner, W., and Kistler, W. (2002). Spiking Neuron Models, Cambridge University Press.","DOI":"10.1017\/CBO9780511815706"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Izhikevich, E. (2007). Dynamical Systems in Neuroscience: The Geometry of Excitability and Bursting, MIT Press.","DOI":"10.7551\/mitpress\/2526.001.0001"},{"key":"ref_16","unstructured":"Ermentrout, G.B., and Terman, D. (2010). Foundations of Mathematical Neuroscience, Springer."},{"key":"ref_17","first-page":"409","article-title":"Increase in complexity in random neural networks","volume":"5","author":"Cessac","year":"1995","journal-title":"J. Phys. I"},{"key":"ref_18","unstructured":"Moynot, O. (2000). Etude math\u00e9matique de la dynamique des r\u00e9seaux neuronaux al\u00e9atoires r\u00e9currents. [Ph.D. Thesis, Universit\u00e9 Paul Sabatier]."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s004400100182","article-title":"Large deviations and mean-field theory for asymmetric random recurrent neural networks","volume":"123","author":"Moynot","year":"2002","journal-title":"Probab. Theory Relat. Fields."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1140\/epjst\/e2007-00058-2","article-title":"From neuron to neural networks dynamics","volume":"142","author":"Cessac","year":"2007","journal-title":"Eur. Phys. J. Spec. Top."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1140\/epjst\/e2007-00059-1","article-title":"Random Recurrent Neural Networks","volume":"142","author":"Samuelides","year":"2007","journal-title":"Eur. Phys. J. Spec. Top."},{"key":"ref_22","unstructured":"Kandel, E., Schwartz, J., and Jessel, T. (2000). Principles of Neural Science, McGraw-Hill. [4th ed]."},{"key":"ref_23","unstructured":"Dayan, P., and Abbott, L. (2001). Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems, MIT Press."},{"key":"ref_24","unstructured":"Rudin, W. (1987). Real and Complex Analysis, McGraw-Hill."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1103\/PhysRevLett.78.350","article-title":"Glassy behaviour in disordered systems with nonrelaxational dynamics","volume":"78","author":"Cugliandolo","year":"1997","journal-title":"Phys. Rev. Lett."},{"key":"ref_26","first-page":"620","article-title":"Recherches quantitatifs sur l\u2019excitation des nerfs traitee comme une polarisation","volume":"9","author":"Lapicque","year":"1907","journal-title":"J. Physiol. Paris."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Daley, D., and Vere-Jones, D. (2007). An Introduction to the Theory of Point Processes: General Theory and Structure, Springer.","DOI":"10.1007\/978-0-387-49835-5"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1103\/PhysRevLett.71.312","article-title":"Coherence and incoherence in a globally coupled ensemble of pulse-emitting units","volume":"71","author":"Gerstner","year":"1993","journal-title":"Phys. Rev. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1103\/PhysRevE.51.738","article-title":"Time structure of the activity in neural network models","volume":"51","author":"Gerstner","year":"1995","journal-title":"Phys. Rev. E"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"C\u00e1ceres, M.J., Carillo, J.A., and Perhame, B. (2011). Analysis of nonlinear noisy integrate and fire neuron models: Blow-up and steady states. J. Math. Neurosci., 1.","DOI":"10.1186\/2190-8567-1-7"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Baladron, J., Fasoli, D., Faugeras, O., and Touboul, J. (2012). Mean-field description and propagation of chaos in networks of Hodgkin-Huxley and FitzHugh-Nagumo neurons. J. Math. Neurosci., 2.","DOI":"10.1186\/2190-8567-2-10"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Bogachev, V. (2007). Measure Theory, Springer. [1 ed].","DOI":"10.1007\/978-3-540-34514-5"},{"key":"ref_33","unstructured":"When N is even the formulae are slightly more complicated but all the results we prove below in the case N odd are still valid."},{"key":"ref_34","unstructured":"We note Np(m,\u03a3) the law of the p-dimensional Gaussian variable with mean m and covariance matrix \u03a3."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ellis, R. (1985). Entropy, Large Deviations and Statistical Mechanics, Springer.","DOI":"10.1007\/978-1-4613-8533-2"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Liggett, T.M. (2005). Interacting Particle Systems, Springer.","DOI":"10.1007\/b138374"},{"key":"ref_37","unstructured":"Deuschel, J.D., and Stroock, D.W. (1989). Large Deviations, Academic Press."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Dembo, A., and Zeitouni, O. (1997). Large Deviations Techniques, Springer. [2nd ed].","DOI":"10.1007\/978-1-4612-5320-4"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/BF01206186","article-title":"Large deviations for stationary Gaussian processes","volume":"97","author":"Donsker","year":"1985","journal-title":"Commun. Math. Phys."},{"key":"ref_40","unstructured":"Bergulson, V. (1993). Convergence in Ergodic Theory and Probability, De Gruyter."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1002\/cpa.3160360204","article-title":"Asymptotic Evaluation of Certain Markov Process Expectations for Large Time, IV","volume":"XXXVI","author":"Donsker","year":"1983","journal-title":"Commun. Pure Appl. Math."},{"key":"ref_42","unstructured":"Faugeras, O., and MacLaurin, J. (2013). A Large Deviation Principle and an Analytical Expression of the Rate Function for a Discrete Stationary Gaussian Process, arXiv, 1311.4400."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1007\/BF00353880","article-title":"The Large Deviation Principle for Hypermixing Processes","volume":"78","author":"Chiyonobu","year":"1988","journal-title":"Probab. Theory Relat. Fields."},{"key":"ref_44","unstructured":"We noted in the introduction that this is termed propagation of chaos by some."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1488","DOI":"10.1137\/090756971","article-title":"Stochastic neural field theory and the system-size expansion","volume":"70","author":"Bressloff","year":"2009","journal-title":"SIAM J. Appl. Math."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Buice, M., and Cowan, J. (2007). Field-theoretic approach to fluctuation effects in neural networks. Phys. Rev. E, 75.","DOI":"10.1103\/PhysRevE.75.051919"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"3171","DOI":"10.1103\/PhysRevE.50.3171","article-title":"Theory of correlations in stochastic neural networks","volume":"50","author":"Ginzburg","year":"1994","journal-title":"Phys. Rev. E"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1162\/neco.2009.02-08-710","article-title":"A master equation formalism for macroscopic modeling of asynchronous irregular activity states","volume":"21","author":"ElBoustani","year":"2009","journal-title":"Neural Comput."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1162\/neco.2009.02-09-960","article-title":"Systematic fluctuation expansion for neural network activity equations","volume":"22","author":"Buice","year":"2010","journal-title":"Neural Comput."},{"key":"ref_50","unstructured":"Neveu, J. (1968). Processus al\u00e9atoires gaussiens, Presses de l\u2019Universit\u00e9 de Montr\u00e9al."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/17\/7\/4701\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T20:48:46Z","timestamp":1760215726000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/17\/7\/4701"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,6]]},"references-count":50,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2015,7]]}},"alternative-id":["e17074701"],"URL":"https:\/\/doi.org\/10.3390\/e17074701","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,7,6]]}}}