English
Related papers

Related papers: Pattern recognition in Deep Boltzmann machines

200 papers

In this paper we study the properties of the quenched pressure of a multi-layer spin-glass model (a deep Boltzmann Machine in artificial intelligence jargon) whose pairwise interactions are allowed between spins lying in adjacent layers and…

Statistical Mechanics · Physics 2020-02-26 Diego Alberici , Adriano Barra , Pierluigi Contucci , Emanuele Mingione

In this paper we adapt the broken replica interpolation technique (developed by Francesco Guerra to deal with the Sherrington-Kirkpatrick model, namely a pairwise mean-field spin-glass whose couplings are i.i.d. standard Gaussian variables)…

Mathematical Physics · Physics 2020-06-02 Elena Agliari , Linda Albanese , Adriano Barra , Gabriele Ottaviani

The interpolation techniques have become, in the past decades, a powerful approach to lighten several properties of spin glasses within a simple mathematical framework. Intrinsically, for their construction, these schemes were naturally…

Disordered Systems and Neural Networks · Physics 2015-10-27 Adriano Barra , Francesco Guerra , Emanuele Mingione

We consider a system composed by N atoms trapped within a multimode cavity, whose theoretical description is captured by a disordered multimode Dicke model. We show that in the resonant, zero field limit the system exactly realizes the…

Disordered Systems and Neural Networks · Physics 2015-01-16 Pietro Rotondo , Enrico Tesio , Sergio Caracciolo

Some interesting recent advances in the theoretical understanding of neural networks have been informed by results from the physics of disordered many-body systems. Motivated by these findings, this work uses the replica technique to study…

Disordered Systems and Neural Networks · Physics 2018-08-17 Gavin Hartnett , Edward Parker , Edward Geist

A class of deep Boltzmann machines is considered in the simplified framework of a quenched system with Gaussian noise and independent entries. The quenched pressure of a $K$-layers spin glass model is studied allowing interactions only…

Mathematical Physics · Physics 2021-08-04 Diego Alberici , Pierluigi Contucci , Emanuele Mingione

The concept of replica symmetry breaking found in the solution of the mean-field Sherrington-Kirkpatrick spin-glass model has been applied to a variety of problems in science ranging from biological to computational and even financial…

Disordered Systems and Neural Networks · Physics 2008-03-25 Helmut G. Katzgraber , Alexander K. Hartmann , A. P. Young

Understanding the glassy nature of neural networks is pivotal both for theoretical and computational advances in Machine Learning and Theoretical Artificial Intelligence. Keeping the focus on dense associative Hebbian neural networks, the…

Disordered Systems and Neural Networks · Physics 2022-09-28 Linda Albanese , Francesco Alemanno , Andrea Alessandrelli , Adriano Barra

The spherical version of the Hopfield model for pattern recognition is considered in the static limit. Structures inside the patterns are modeled by Gaussian random variables that reward correlation between pairs of spins in a given…

Disordered Systems and Neural Networks · Physics 2026-03-11 Theodorus Maria Nieuwenhuizen

By controlling quantum fluctuations via the Falk-Bruch inequality we give the first rigorous argument for the existence of a spin-glass phase in the quantum Sherrington-Kirkpatrick model with a transverse magnetic field if the temperature…

Disordered Systems and Neural Networks · Physics 2021-11-16 Hajo Leschke , Chokri Manai , Rainer Ruder , Simone Warzel

We consider restricted Boltzmann machines with a binary visible layer and a Gaussian hidden layer trained by an unlabelled dataset composed of noisy realizations of a single ground pattern. We develop a statistical mechanics framework to…

Disordered Systems and Neural Networks · Physics 2024-06-17 Alberto Fachechi , Elena Agliari , Miriam Aquaro , Anthony Coolen , Menno Mulder

We introduce a Sherrington-Kirkpatrick spin-glass model with the addition of elastic degrees of freedom. The problem is formulated in terms of an effective four-spin Hamiltonian in the pressure ensemble, which can be treated by the replica…

Disordered Systems and Neural Networks · Physics 2009-04-30 D. B. Liarte , S. R. Salinas , C. S. O. Yokoi

We study spin glasses on random lattices with finite connectivity. In the infinite connectivity limit they reduce to the Sherrington Kirkpatrick model. In this paper we investigate the expansion around the high connectivity limit. Within…

Disordered Systems and Neural Networks · Physics 2009-11-07 Giorgio Parisi , Francesca Tria

The Sherrington-Kirkpatrick (SK) is a foundational model for understanding spin glass systems. It is based on the pairwise interaction between each two spins in a fully connected lattice with quenched disordered interactions. The nature of…

Disordered Systems and Neural Networks · Physics 2025-06-30 Ali Talebi

The Sherrington-Kirkpatrick spin-glass model used the replica symmetry method to find the phase transition of the system. In 1979-1980, Parisi proposed a solution based on replica symmetry breaking (RSB), which allowed him to identify the…

Disordered Systems and Neural Networks · Physics 2024-11-08 Ali Talebi , Mahsa Bagherikalhor , Behrouz Askari , G. Reza Jafari

The mean field theory of a spin glass with a specific form of nearest and next nearest neighbor interactions is investigated. Depending on the sign of the interaction matrix chosen we either find the continuous replica symmetry breaking…

Disordered Systems and Neural Networks · Physics 2007-05-23 D. S. Dean , F. Ritort

By using a simple interpolation argument, in previous work we have proven the existence of the thermodynamic limit, for mean field disordered models, including the Sherrington-Kirkpatrick model, and the Derrida p-spin model. Here we extend…

Disordered Systems and Neural Networks · Physics 2007-05-23 Francesco Guerra

We investigate the large deviation behavior of the overlap probability density in the Sherrington--Kirkpatrick model from several analytical perspectives. First we analyze the spin glass phase using the coupled replica scheme. Here…

Statistical Mechanics · Physics 2009-11-07 Alain Billoire , Silvio Franz , Enzo Marinari

We study the quenched complexity in spin-glass mean-field models satisfying the Becchi-Rouet-Stora-Tyutin supersymmetry. The outcome of such study, consistent with recent numerical results, allows, in principle, to conjecture the absence of…

Disordered Systems and Neural Networks · Physics 2009-11-10 A. Crisanti , L. Leuzzi , G. Parisi , T. Rizzo

We study hierarchies of replica-symmetry-breaking solutions of the Sherrington-Kirkpatrick model. Stationarity equations for order parameters of solutions with an arbitrary number of hierarchies are set and the limit to infinite number of…

Disordered Systems and Neural Networks · Physics 2008-09-16 V Janis , A. Klic , M. Ringel
‹ Prev 1 2 3 10 Next ›