English
Related papers

Related papers: Dynamical stability for dense patterns in discrete…

200 papers

Deep neural networks are known to suffer from exploding or vanishing gradients as depth increases, a phenomenon closely tied to the spectral behavior of the input-output Jacobian. Prior work has identified critical initialization schemes…

Machine Learning · Computer Science 2025-11-25 Benjamin Dadoun , Soufiane Hayou , Hanan Salam , Mohamed El Amine Seddik , Pierre Youssef

We analyse the stability of linear dynamical systems defined on sparse, random graphs with predator-prey, competitive, and mutualistic interactions. These systems are aimed at modelling the stability of fixed points in large systems defined…

Statistical Mechanics · Physics 2025-01-30 Andrea Marcello Mambuca , Chiara Cammarota , Izaak Neri

In this paper, we provide sufficient conditions for dissipativity and local asymptotic stability of discrete-time dynamical systems parametrized by deep neural networks. We leverage the representation of neural networks as pointwise affine…

Machine Learning · Computer Science 2022-06-09 Jan Drgona , Soumya Vasisht , Aaron Tuor , Draguna Vrabie

It is well known that a sparsely coded network in which the activity level is extremely low has intriguing equilibrium properties. In the present work, we study the dynamical properties of a neural network designed to store sparsely coded…

Disordered Systems and Neural Networks · Physics 2009-10-31 Katsunori Kitano , Toshio Aoyagi

We study the storage of multiple phase-coded patterns as stable dynamical attractors in recurrent neural networks with sparse connectivity. To determine the synaptic strength of existent connections and store the phase-coded patterns, we…

Neurons and Cognition · Quantitative Biology 2015-05-28 Siliva Scarpetta , Ferdinando Giacco , Antonio de Candia

We investigate dynamical systems characterized by a time series of distinct semi-stable activity patterns, as they are observed in cortical neural activity patterns. We propose and discuss a general mechanism allowing for an adiabatic…

Disordered Systems and Neural Networks · Physics 2010-02-11 Claudius Gros

We analytically determine the number and distribution of fixed points in a canonical model of a chaotic neural network. This distribution reveals that fixed points and dynamics are confined to separate shells in phase space. Furthermore,…

Disordered Systems and Neural Networks · Physics 2023-12-12 Jakob Stubenrauch , Christian Keup , Anno C. Kurth , Moritz Helias , Alexander van Meegen

Network motifs are the building blocks of complex networks and are significantly involved in the network dynamics such as information processing and local operations in the brain, biological marks for drug targets, identifying and…

Physics and Society · Physics 2023-04-25 Bnaya Gross , Shlomo Havlin , Baruch Barzel

For infinitely large sparse networks of spiking neurons mean field theory shows that a balanced state of highly irregular activity arises under various conditions. Here we analytically investigate the microscopic irregular dynamics in…

Disordered Systems and Neural Networks · Physics 2009-11-13 Sven Jahnke , Raoul-Martin Memmesheimer , Marc Timme

We consider a deep structured linear network under sparsity constraints. We study sharp conditions guaranteeing the stability of the optimal parameters defining the network. More precisely, we provide sharp conditions on the network…

Optimization and Control · Mathematics 2023-02-03 Francois Malgouyres

Combinatorial threshold-linear networks (CTLNs) are a special class of recurrent neural networks whose dynamics are tightly controlled by an underlying directed graph. Recurrent networks have long been used as models for associative memory…

Neurons and Cognition · Quantitative Biology 2023-11-21 Carina Curto , Jesse Geneson , Katherine Morrison

Self-sustained, elevated neuronal activity persisting on time scales of ten seconds or longer is thought to be vital for aspects of working memory, including brain representations of real space. Continuous-attractor neural networks, one of…

Neurons and Cognition · Quantitative Biology 2020-08-19 Joseph L. Natale , H. George E. Hentschel , Ilya Nemenman

Relationship for dynamical properties in the vicinity of fixed points between two-dimensional continuous and its positivity-preserving discretized dynamical systems is studied. Based on linear stability analysis, we reveal the conditions…

Chaotic Dynamics · Physics 2023-04-05 Shousuke Ohmori , Yoshihiro Yamazaki

We consider a system of several nonlinear equations with a distributed delay and obtain absolute asymptotic stability conditions, independent of the delay. The ideas of the proofs are based on the notion of a strong attractor. The results…

Dynamical Systems · Mathematics 2021-05-26 Leonid Berezansky , Elena Braverman

Persistent activity in neuronal populations has been shown to represent the spatial position of remembered stimuli. Networks that support bump attractors are often used to model such persistent activity. Such models usually exhibit…

Neurons and Cognition · Quantitative Biology 2013-08-26 Sam Carroll , Kresimir Josic , Zachary P Kilpatrick

Threshold-linear networks are a common class of firing rate models that describe recurrent interactions among neurons. Unlike their linear counterparts, these networks generically possess multiple stable fixed points (steady states), making…

Neurons and Cognition · Quantitative Biology 2016-12-28 Carina Curto , Katherine Morrison

We study the stability of the dynamics of a network of n neurons intercting linearly through a random gaussian matrix of excitatory and inhibitory type. Using the aproach developed in a previous paper we show some interesting properties of…

Mathematical Physics · Physics 2011-11-10 J. F. Feng , M. Shcherbina , B. Tirozzi

Dense associative memory, a fundamental instance of modern Hopfield networks, can store a large number of memory patterns as equilibrium states of recurrent networks. While the stationary-state storage capacity has been investigated, its…

Disordered Systems and Neural Networks · Physics 2025-10-29 Kazushi Mimura , Jun'ichi Takeuchi , Yuto Sumikawa , Yoshiyuki Kabashima , Anthony C. C. Coolen

Neural networks are becoming increasingly popular in applications, but our mathematical understanding of their potential and limitations is still limited. In this paper, we further this understanding by developing statistical guarantees for…

Machine Learning · Computer Science 2022-12-13 Johannes Lederer

Dynamical networks with time delays can pose a considerable challenge for mathematical analysis. Here, we extend the approach of generalized modeling to investigate the stability of large networks of delay-coupled delay oscillators. When…

Disordered Systems and Neural Networks · Physics 2011-11-11 Johannes M. Höfener , Gautam C. Sethia , Thilo Gross
‹ Prev 1 2 3 10 Next ›