English
Related papers

Related papers: From Dyson to Hopfield: Processing on hierarchical…

200 papers

Dense Associative Memories or modern Hopfield networks permit storage and reliable retrieval of an exponentially large (in the dimension of feature space) number of memories. At the same time, their naive implementation is non-biological,…

Neurons and Cognition · Quantitative Biology 2021-04-29 Dmitry Krotov , John Hopfield

We introduce and study a new model of interacting neural networks, incorporating the spatial dimension (e.g. position of neurons across the cortex) and some learning processes. The dynamic of each neural network is described via the elapsed…

Analysis of PDEs · Mathematics 2020-09-03 Delphine Salort , Nicolas Torres

Workhorse theories throughout all of physics derive effective Hamiltonians to describe slow time evolution, even though low-frequency modes are actually coupled to high-frequency modes. Such effective Hamiltonians are accurate because of…

Classical Physics · Physics 2017-01-25 Lukas Gilz , Eike P. Thesing , James R. Anglin

Recent advances in experimental techniques enable the simultaneous recording of activity from thousands of neurons in the brain, presenting both an opportunity and a challenge: to build meaningful, scalable models of large neural…

Biological Physics · Physics 2025-08-05 Luca Di Carlo , Francesca Mignacco , Christopher W. Lynn , William Bialek

In this paper we study Markov processes and related first passage problems on a class of weighted, modular graphs which generalize the Dyson hierarchical model. In these networks, the coupling strength between two nodes depends on their…

Data Analysis, Statistics and Probability · Physics 2017-04-11 Flavia Tavani , Elena Agliari

We report on both analytical and numerical results concerning stochastic Hopfield--like neural automata exhibiting the following (biologically inspired) features: (1) Neurons and synapses evolve in time as in contact with respective baths…

Statistical Mechanics · Physics 2007-05-23 J. J. Torres , J. Marro , P. L. Garrido , J. M. Cortes , F. Ramos , M. A. Munoz

The mutual information, I, of the three-state neural network can be obtained exactly for the mean-field architecture, as a function of three macroscopic parameters: the overlap, the neural activity and the {\em activity-overlap}, i.e. the…

Statistical Mechanics · Physics 2007-05-23 David R. Dominguez Carreta , Elka Korutcheva

A pervasive challenge in neuroscience is testing whether neuronal connectivity changes over time due to specific causes, such as stimuli, events, or clinical interventions. Recent hardware innovations and falling data storage costs enable…

Neurons and Cognition · Quantitative Biology 2024-01-05 Johan Medrano , Karl J. Friston , Peter Zeidman

Recent experiments have shown that training trajectories of multiple deep neural networks with different architectures, optimization algorithms, hyper-parameter settings, and regularization methods evolve on a remarkably low-dimensional…

Machine Learning · Computer Science 2025-11-19 Jialin Mao , Itay Griniasty , Yan Sun , Mark K. Transtrum , James P. Sethna , Pratik Chaudhari

We prove that the general mean-field type networks at low load behave in accordance with the Poisson Hypothesis. That means that the network equilibrates in time independent of its size. This is a "high-temperature" counterpart of our…

Mathematical Physics · Physics 2008-11-24 Alexander Rybko , Senya Shlosman , Alexander Vladimirov

It is shown that a Hopfield recurrent neural network exhibits a scaling regime, whose specific exponents depend on the number of parcels used and the decay length of the coupling strength. This scaling regime recovers the picture introduced…

Disordered Systems and Neural Networks · Physics 2025-02-17 Giorgio Gosti , Sauro Succi , Giancarlo Ruocco

Non-interacting particles obeying certain fractional statistics have been predicted to exhibit superconductivity. We discuss the issue in an attractively interacting system of spinful semions on a lattice by numerically investigating the…

Superconductivity · Physics 2023-01-02 Koji Kudo , Jonathan Schirmer

We study the Hopfield model on a random graph in scaling regimes where the average number of connections per neuron is a finite number and where the spin dynamics is governed by a synchronous execution of the microscopic update rule…

Condensed Matter · Physics 2016-08-16 I. Pérez Castillo , N. S. Skantzos

The paper deals with non-linear Poisson neuron network models with bounded memory dynamics, that can include both Hebbian learning mechanisms and refractory periods. The state of a network is described by the times elapsed since its neurons…

Probability · Mathematics 2012-06-21 Konstantin Borovkov , Geoffrey Decrouez , Matthieu Gilson

The Hopfield associative memory model stores random patterns in synaptic couplings according to Hebb's rule and retrieves them through gradient descent on an energy function. This conventional setting, where neurons are assumed to have…

Disordered Systems and Neural Networks · Physics 2026-01-23 Yoshiyuki Kabashima , Kazushi Mimura

Hierarchical Bayesian models are increasingly used in large, inhomogeneous complex network dynamical systems by modeling parameters as draws from a hyperparameter-governed distribution. However, theoretical guarantees for these estimates as…

Statistics Theory · Mathematics 2026-01-23 Yi Yu , Yubo Hou , Yinchong Wang , Nan Zhang , Jianfeng Feng , Wenlian Lu

Based on a rigorous extension of classical statistical mechanics to networks, we study a specific microscopic network Hamiltonian. The form of this Hamiltonian is derived from the assumption that individual nodes increase/decrease their…

Statistical Mechanics · Physics 2015-06-25 Christoly Biely , Stefan Thurner

The Hopfield model is a paradigmatic model of neural networks that has been analyzed for many decades in the statistical physics, neuroscience, and machine learning communities. Inspired by the manifold hypothesis in machine learning, we…

Disordered Systems and Neural Networks · Physics 2023-05-01 Matteo Negri , Clarissa Lauditi , Gabriele Perugini , Carlo Lucibello , Enrico Malatesta

We investigate a Hamiltonian model of networks. The model is a mirror formulation of the XY model (hence the name) -- instead letting the XY spins vary, keeping the coupling topology static, we keep the spins conserved and sample different…

Computational Physics · Physics 2009-09-30 Petter Holme , Zhi-Xi Wu , Petter Minnhagen

High-order extensions of the Hopfield model are known to exhibit dramatically enhanced storage capacity at equilibrium, while their dynamical retrieval properties remain less well understood. In our previous work, we carried out a dynamical…

Statistical Mechanics · Physics 2026-04-06 Yuto Sumikawa , Yoshiyuki Kabashima