English
Related papers

Related papers: Large deviations for randomly connected neural net…

200 papers

The purpose of this paper is to analyze how the disorder affects the dynamics of critical fluctuations for two different types of interacting particle system: the Curie-Weiss and Kuramoto model. The models under consideration are a…

Probability · Mathematics 2011-11-16 Francesca Collet , Paolo Dai Pra

We investigate systems of interacting stochastic differential equations with two kinds of heterogeneity: one originating from different weights of the linkages, and one concerning their asymptotic relevance when the system becomes large. To…

Probability · Mathematics 2020-06-02 Carsten Chong , Claudia Klüppelberg

We consider finite dynamical networks and define internal reliability according to the synchronization properties of a replicated unit or a set of units. If the states of the replicated units coincide with their prototypes, they are…

Adaptation and Self-Organizing Systems · Physics 2025-01-03 Tommaso Matteuzzi , Franco Bagnoli , Michele Baia , Stefano Iubini , Arkady Pikovsky

In this paper we extend the results of Lenci and Rey-Bellet on the large deviation upper bound of the distribution measures of local Hamiltonians with respect to a Gibbs state, in the setting of translation-invariant finite-range…

Mathematical Physics · Physics 2009-11-13 Fumio Hiai , Milan Mosonyi , Tomohiro Ogawa

The Kuramoto model of coupled phase oscillators on small-world (SW) graphs is analyzed in this work. When the number of oscillators in the network goes to infinity, the model acquires a family of steady state solutions of degree q, called…

Adaptation and Self-Organizing Systems · Physics 2015-06-16 Georgi S. Medvedev

We study pattern formation in class of a large-dimensional neural networks posed on random graphs and subject to spatio-temporal stochastic forcing. Under generic conditions on coupling and nodal dynamics, we prove that the network admits a…

Probability · Mathematics 2025-08-26 Daniele Avitabile , James MacLaurin

Neural networks of the brain form one of the most complex systems we know. Many qualitative features of the emerging collective phenomena, such as correlated activity, stability, response to inputs, chaotic and regular behavior, can,…

Disordered Systems and Neural Networks · Physics 2016-06-16 Jannis Schuecker , Sven Goedeke , David Dahmen , Moritz Helias

Understanding the relationship between the heterogeneous structure of complex networks and cooperative phenomena occurring on them remains a key problem in network science. Mean-field theories of spin models on networks constitute a…

Disordered Systems and Neural Networks · Physics 2022-02-10 Fernando L. Metz , Thomas Peron

We consider a mean-field model of coupled phase oscillators with quenched disorder in the natural frequencies and coupling strengths. A fraction $p$ of oscillators are positively coupled, attracting all others, while the remaining fraction…

Statistical Mechanics · Physics 2016-11-03 Hyunsuk Hong , Kevin P. O'Keeffe , Steven H. Strogatz

The deterministic dynamics of randomly connected neural networks are studied, where a state of binary neurons evolves according to a discreet-time synchronous update rule. We give a theoretical support that the overlap of systems' states…

Statistical Mechanics · Physics 2015-03-10 Taro Toyoizumi , Haiping Huang

Focusing on stochastic systems arising in mean-field models, the systems under consideration belong to the class of switching diffusions, in which continuous dynamics and discrete events coexist and interact. The discrete events are modeled…

Probability · Mathematics 2019-01-18 Son L. Nguyen , George Yin , Tuan A. Hoang

The Network Disturbance Model of Doreian (1989) expresses the dependency between observations taken at the vertices of a network by modelling the correlation between neighbouring vertices, using a single correlation parameter $\rho$. It has…

Statistics Theory · Mathematics 2021-05-10 A. D. Barbour , Gesine Reinert

We investigate large deviations for the empirical measure of the position and momentum of a particle traveling in a box with hot walls. The particle travels with uniform speed from left to right, until it hits the right boundary. Then it is…

Probability · Mathematics 2011-03-16 Raphael Lefevere , Mauro Mariani , Lorenzo Zambotti

The large deviations at 'Level 2.5 in time' for time-dependent ensemble-empirical-observables, introduced by C. Maes, K. Netocny and B. Wynants [Markov Proc. Rel. Fields. 14, 445 (2008)] for the case of $N$ independent Markov jump…

Statistical Mechanics · Physics 2021-05-12 Cecile Monthus

We propose a general framework to extract microscopic interactions from raw configurations with deep neural networks. The approach replaces the modeling Hamiltonian by the neural networks, in which the interaction is encoded. It can be…

Computational Physics · Physics 2020-08-19 Lingxiao Wang , Yin Jiang , Kai Zhou

This paper is devoted to the problem of sample path large deviations for multidimensional queueing models with feedback. We derive a new version of the contraction principle where the continuous map is not well-defined on the whole space:…

Probability · Mathematics 2007-05-23 Marc Lelarge

We consider an adaptive network, whose connection weights co-evolve in congruence with the dynamical states of the local nodes that are under the influence of an external stimulus. The adaptive dynamical system mimics the adaptive synaptic…

Disordered Systems and Neural Networks · Physics 2022-04-06 S. Thamizharasan , V. K. Chandrasekar , M. Senthilvelan , Rico Berner , Eckehard Schoell , D. V. Senthilkumar

We consider a two-dimensional Hamiltonian system perturbed by a small diffusion term, whose coefficient is state-dependent and non-degenerate. As a result, the process consists of the fast motion along the level curves and slow motion…

Probability · Mathematics 2022-05-24 Shuo Yan

This paper is a review dealing with the study of large size random recurrent neural networks. The connection weights are selected according to a probability law and it is possible to predict the network dynamics at a macroscopic scale using…

Mathematical Physics · Physics 2011-11-10 M. Samuelides , B. Cessac

We consider particle systems with mean-field interactions whose distribution is invariant by translations. Under the assumption that the system seen from its centre of mass be reversible with respect to a Gibbs measure, we establish large…

Probability · Mathematics 2019-04-25 Julien Reygner