English
Related papers

Related papers: Pattern recognition in Deep Boltzmann machines

200 papers

We discuss the mean-field theory of spin-glass models with frustrated long-range random spin exchange. We analyze the reasons for breakdown of the simple mean-field theory of Sherrington and Kirkpatrick. We relate the replica-symmetry…

Disordered Systems and Neural Networks · Physics 2015-06-24 Václav Janiš

Using Monte Carlo simulations, we study in detail the overlap distribution for individual samples for several spin-glass models including the infinite-range Sherrington-Kirkpatrick model, short-range Edwards-Anderson models in three and…

Disordered Systems and Neural Networks · Physics 2014-10-29 Matthew Wittmann , B. Yucesoy , Helmut G. Katzgraber , J. Machta , A. P. Young

Restricted Boltzmann Machines are described by the Gibbs measure of a bipartite spin glass, which in turn corresponds to the one of a generalised Hopfield network. This equivalence allows us to characterise the state of these systems in…

Disordered Systems and Neural Networks · Physics 2018-02-28 Adriano Barra , Giuseppe Genovese , Peter Sollich , Daniele Tantari

We analyze the replica-symmetry-breaking construction in the Sherrington-Kirkpatrick model of a spin glass. We present a general scheme for deriving an exact asymptotic behavior near the critical temperature of the solution with an…

Disordered Systems and Neural Networks · Physics 2008-09-16 V. Janis , A. Klic

Restricted Boltzmann Machines are key tools in Machine Learning and are described by the energy function of bipartite spin-glasses. From a statistical mechanical perspective, they share the same Gibbs measure of Hopfield networks for…

Mathematical Physics · Physics 2017-08-02 Elena Agliari , Adriano Barra , Chiara Longo , Daniele Tantari

We study a variant of the Sherrington-Kirkpatrick (S-K) spin glass model with external field, where the random symmetric couplings matrix does not consist of i.i.d. entries but is instead orthogonally invariant in law. For sufficiently high…

Probability · Mathematics 2024-05-01 Zhou Fan , Yihong Wu

Unsupervised learning in a generalized Hopfield associative-memory network is investigated in this work. First, we prove that the (generalized) Hopfield model is equivalent to a semi-restricted Boltzmann machine with a layer of visible…

Neural and Evolutionary Computing · Computer Science 2017-07-26 Huiling Zhen , Shang-Nan Wang , Hai-Jun Zhou

Spin glass models involving multiple replicas with constrained overlaps have been studied in [FPV92; PT07; Pan18a]. For the spherical versions of these models [Ko19; Ko20] showed that the limiting free energy is given by a Parisi type…

Probability · Mathematics 2023-04-11 David Belius , Leon Fröber , Justin Ko

During the last years, through the combined effort of the insight, coming from physical intuition and computer simulation, and the exploitation of rigorous mathematical methods, the main features of the mean field Sherrington-Kirkpatrick…

Disordered Systems and Neural Networks · Physics 2015-05-18 Adriano Barra , Aldo Di Biasio , Francesco Guerra

In the Sherrington-Kirkpatrick (SK) and related mixed $p$-spin models, there is interest in understanding replica symmetry breaking at low temperatures. For this reason, the so-called AT line proposed by de Almeida and Thouless as a…

Probability · Mathematics 2025-07-09 Erik Bates , Leila Sloman , Youngtak Sohn

We study the Potts spin glass model, which generalizes the Sherrington-Kirkpatrick model to the case when spins take more than two values but their interactions are counted only if the spins are equal. We obtain the analogue of the Parisi…

Probability · Mathematics 2018-03-28 Dmitry Panchenko

The Sherrington--Kirkpatrick model of spin glasses, the Hopfield model of neural networks and the Ising spin glass are all models of binary data belonging to the one-parameter exponential family with quadratic sufficient statistic. Under…

Probability · Mathematics 2007-12-18 Sourav Chatterjee

In the last five decades, mean-field neural-networks have played a crucial role in modelling associative memories and, in particular, the Hopfield model has been extensively studied using tools borrowed from the statistical mechanics of…

Disordered Systems and Neural Networks · Physics 2024-09-17 Elena Agliari , Adriano Barra , Pierluigi Bianco , Alberto Fachechi , Diego Pallara

In this work, we first revise some extensions of the standard Hopfield model in the low storage limit, namely the correlated attractor case and the multitasking case recently introduced by the authors. The former case is based on a…

Disordered Systems and Neural Networks · Physics 2012-05-23 Elena Agliari , Adriano Barra , Andrea De Antoni , Andrea Galluzzi

We introduce a systematic method for expanding general spin-glass Hamiltonians in terms of Mattis interactions, providing a novel perspective for understanding the fundamental differences between short-range Edwards-Anderson (EA) and…

Disordered Systems and Neural Networks · Physics 2026-04-01 Mutian Shen , Zohar Nussinov , Yang-Yu Liu

A quantum Parisi formula for the transverse field Sherrington-Kirkpatrick (SK) model is proven with an elementary mathematical method. First, a self-overlap corrected quantum model of the transverse field SK model is represented in terms of…

Mathematical Physics · Physics 2025-12-17 C. Itoi , K. Fujiwara , Y. Sakamoto

In this paper a multi-scale version of the Sherrington and Kirkpatrick model is introduced and studied. The pressure per particle in the thermodynamical limit is proved to obey a variational principle of Parisi type. The result is achieved…

Mathematical Physics · Physics 2019-02-20 Pierluigi Contucci , Emanuele Mingione

We consider an invariant random matrix model where the standard Gaussian potential is distorted by an additional single pole of order $m$. We compute the average or macroscopic spectral density in the limit of large matrix size, solving the…

Mathematical Physics · Physics 2014-07-09 Gernot Akemann , Dario Villamaina , Pierpaolo Vivo

In this paper we continue our investigation on the high storage regime of a neural network with Gaussian patterns. Through an exact mapping between its partition function and one of a bipartite spin glass (whose parties consist of Ising and…

Disordered Systems and Neural Networks · Physics 2015-06-05 Adriano Barra , Giuseppe Genovese , Francesco Guerra , Daniele Tantari

We investigate near the point of glass transition the expansion of the free energy corresponding to the generalized Sherrington--Kirkpatrick model with arbitrary diagonal operators U standing instead of Ising spins. We focus on the case…

Statistical Mechanics · Physics 2013-03-07 E. E. Tareyeva , T. I. Schelkacheva , N. M. Chtchelkatchev