English
Related papers

Related papers: How glassy are neural networks?

200 papers

We have studied numerically the states reached in a quench from various temperatures in the one-dimensional fully-connected Kotliar, Anderson and Stein Ising spin glass model. This is a model where there are long-range interactions between…

Statistical Mechanics · Physics 2018-05-25 Auditya Sharma , Joonhyun Yeo , M. A. Moore

We introduce a mean field spin glass model with gaussian distribuited spins and pairwise interactions, whose couplings are drawn randomly from a normal gaussian distribution too. We completely control the main thermodynamical properties of…

Mathematical Physics · Physics 2012-05-18 Adriano Barra , Giuseppe Genovese , Francesco Guerra , Daniele Tantari

An appropriate model for the random energy landscape in organic glasses is a spatially correlated Gaussian field, generated by randomly located and oriented dipoles and quadrupoles. Correlation properties of energetic disorder directly…

Materials Science · Physics 2013-03-21 S. V. Novikov

Hierarchical spin-glasses are Ising spin models defined by recursively coupling together two equally-sized sub-systems. In this work a new hierarchical spin system is introduced wherein the sub-systems are recursively coupled together…

Disordered Systems and Neural Networks · Physics 2023-04-05 Gavin S Hartnett

We realize a driven-dissipative Ising spin glass using cavity QED in a novel ``4/7" multimode geometry. Gases of ultracold atoms trapped within the cavity by optical tweezers serve as effective spins. They are coupled via randomly signed,…

The authors present empirical distributions for the halting time (measured by the number of iterations to reach a given accuracy) of optimization algorithms applied to two random systems: spin glasses and deep learning. Given an algorithm,…

Machine Learning · Computer Science 2018-12-13 Levent Sagun , Thomas Trogdon , Yann LeCun

Spin-glass systems are universal models for representing many-body phenomena in statistical physics and computer science. High quality solutions of NP-hard combinatorial optimization problems can be encoded into low energy states of…

Disordered Systems and Neural Networks · Physics 2020-01-14 Gavin S. Hartnett , Masoud Mohseni

Glassy behavior is one of the main open problems in condensed matter physics. In this thesis, we approach the problem by studying spin-glasses and colloids, using several complementary strategies. From the point of view of model building,…

Disordered Systems and Neural Networks · Physics 2013-09-10 B. Seoane

Graph convolutional neural networks~(GCNs) have recently demonstrated promising results on graph-based semi-supervised classification, but little work has been done to explore their theoretical properties. Recently, several deep neural…

Machine Learning · Computer Science 2020-02-28 Jilin Hu , Jianbing Shen , Bin Yang , Ling Shao

We analyze the landscape of general smooth Gaussian functions on the sphere in dimension $N$, when $N$ is large. We give an explicit formula for the asymptotic complexity of the mean number of critical points of finite and diverging index…

Probability · Mathematics 2013-12-17 Antonio Auffinger , Gerard Ben Arous

To explore the relation between network structure and function, we studied the computational performance of Hopfield-type attractor neural nets with regular lattice, random, small-world and scale-free topologies. The random net is the most…

Disordered Systems and Neural Networks · Physics 2009-11-10 Patrick N. Mcgraw , Michael Menzinger

Signatures of glassy dynamics have been identified experimentally for a rich variety of materials in which molecular networks provide rigidity. Here we present a theoretical framework to study the glassy behavior of both passive and active…

Statistical Mechanics · Physics 2013-03-26 Shenshen Wang , Peter G. Wolynes

We propose and analyze a new variation of the so-called {\em exponential Hopfield model}, a recently introduced family of associative neural networks with unprecedented storage capacity. Our construction is based on a cost function defined…

Disordered Systems and Neural Networks · Physics 2025-09-09 Linda Albanese , Andrea Alessandrelli , Adriano Barra , Peter Sollich

The structure of continuous Hopfield networks is revisited from a system-theoretic point of view. After adopting a novel electrical network interpretation involving nonlinear capacitors, it is shown that Hopfield networks admit a…

Optimization and Control · Mathematics 2026-01-07 Arjan van der Schaft

We study the free energy of a particle in (arbitrary) high-dimensional Gaussian random potentials with isotropic increments. We prove a computable saddle-point variational representation in terms of a Parisi-type functional for the free…

Probability · Mathematics 2014-02-11 Anton Klimovsky

Networks in machine learning offer examples of complex high-dimensional dynamical systems reminiscent of biological systems. Here, we study the learning dynamics of Generalized Hopfield networks, which permit a visualization of internal…

Disordered Systems and Neural Networks · Physics 2023-12-07 Nacer Eddine Boukacem , Allen Leary , Robin Thériault , Felix Gottlieb , Madhav Mani , Paul François

In this article we study a simple spin model which has a non-interacting Hamiltonian but constrained dynamics. The model, which is a simplification of a purely toplogical cellular model, displays glassy behaviour, involves activated…

Disordered Systems and Neural Networks · Physics 2009-11-07 Lexie Davison , David Sherrington , Juan P. Garrahan , Arnaud Buhot

We analyze the free energy and the overlaps in the 2-spin spherical Sherrington Kirkpatrick spin glass model with an external field for the purpose of understanding the transition between this model and the one without an external field. We…

Disordered Systems and Neural Networks · Physics 2021-05-26 Jinho Baik , Elizabeth Collins-Woodfin , Pierre Le Doussal , Hao Wu

Models of interacting complex systems provide the fundamental statistical physics reference frame for the study and the understanding of associative memories, machine learning, and the dynamics of neural networks. On the other hand,…

We study analytically and numerically a Hopfield fully-connected network with $d$-dimensional vector spins. These networks are models of associative memory that generalize the standard Hopfield with Ising spins, where $P$ examples are…

Disordered Systems and Neural Networks · Physics 2026-02-17 Flavio Nicoletti , Francesco D'Amico , Matteo Negri