English
Related papers

Related papers: How glassy are neural networks?

200 papers

We study rough high-dimensional landscapes in which an increasingly stronger preference for a given configuration emerges. Such energy landscapes arise in glass physics and inference. In particular we focus on random Gaussian functions, and…

Disordered Systems and Neural Networks · Physics 2019-01-09 Valentina Ros , Gerard Ben Arous , Giulio Biroli , Chiara Cammarota

In this paper we discuss a family of models of particle and energy diffusion on a one-dimensional lattice, related to those studied previously in [Sasamoto-Wadati], [Barraquand-Corwin] and [Povolotsky] in the context of KPZ universality…

Mathematical Physics · Physics 2024-05-31 Rouven Frassek , Cristian Giardinà , Jorge Kurchan

Despite the recent success of artificial neural networks, more biologically plausible learning methods may be needed to resolve the weaknesses of backpropagation trained models such as catastrophic forgetting and adversarial attacks.…

Machine Learning · Computer Science 2022-08-09 Ole Christian Eidheim

Recent results are reviewed on both the time evolution and retrieval properties of multi-state neural networks that are based upon spin-glass models. In particular, the properties of models with neuron states having Q-Ising symmetry are…

Disordered Systems and Neural Networks · Physics 2007-05-23 D. Bolle

We have studied the topology of the energy landscape of a spin-glass model and the effect of frustration on it by looking at the connectivity and disconnectivity graphs of the inherent structure. The connectivity network shows the adjacency…

Statistical Mechanics · Physics 2008-03-12 Hamid Seyed-allaei , Hamed Seyed-allaei , Mohammad Reza Ejtehadi

Due to an extremely rugged structure of the free energy landscape, the determination of spin-glass ground states is among the hardest known optimization problems, found to be NP-hard in the most general case. Owing to the specific structure…

Disordered Systems and Neural Networks · Physics 2011-11-10 Martin Weigel

We numerically study dynamical properties of the one-component Gaussian Core Model in the supercooled states. We find that nucleation is suppressed as density increases. Concomitantly the system exhibits glassy slow dynamics characterized…

Soft Condensed Matter · Physics 2015-05-19 Atsushi Ikeda , Kunimasa Miyazaki

In simulations of some infinite range spin glass systems with finite connectivity, it is found that for any resonable computational time, the saturatedenergy per spin that is achieved by a cluster algorithm is lowered in comparison to that…

Condensed Matter · Physics 2016-08-31 N. Persky , I. Kanter , S. Solomon

A complex network is a condensed representation of the relational topological framework of a complex system. A main reason for the existence of such networks is the transmission of items through the entities of these complex systems. Here,…

Physics and Society · Physics 2018-04-18 María Pereda , Ernesto Estrada

The complex dynamics of an increasing number of systems is attributed to the emergence of a rugged energy landscape with an exponential number of metastable states. To develop this picture into a predictive dynamical theory I discuss how to…

Disordered Systems and Neural Networks · Physics 2021-09-15 Tommaso Rizzo

We analyze numerically the training dynamics of deep neural networks (DNN) by using methods developed in statistical physics of glassy systems. The two main issues we address are (1) the complexity of the loss landscape and of the dynamics…

Machine Learning · Statistics 2019-12-23 M. Baity-Jesi , L. Sagun , M. Geiger , S. Spigler , G. Ben Arous , C. Cammarota , Y. LeCun , M. Wyart , G. Biroli

In a recent publication we established an analogy between the free energy of a hard sphere system and the energy of an elastic network [1]. This result enables one to study the free energy landscape of hard spheres, in particular to define…

Disordered Systems and Neural Networks · Physics 2007-08-08 Carolina Brito , Matthieu Wyart

Through a redefinition of patterns in an Hopfield-like model, we introduce and develop an approach to model discrete systems made up of many, interacting components with inner degrees of freedom. Our approach clarifies the intrinsic…

Statistical Mechanics · Physics 2015-05-19 Elena Agliari , Adriano Barra

Many applications in speech, robotics, finance, and biology deal with sequential data, where ordering matters and recurrent structures are common. However, this structure cannot be easily captured by standard kernel functions. To model such…

Machine Learning · Computer Science 2017-10-06 Maruan Al-Shedivat , Andrew Gordon Wilson , Yunus Saatchi , Zhiting Hu , Eric P. Xing

Spherical spin glasses are canonical models for smooth random functions in high dimensions. In this review, we survey several interrelated lines of research on their geometric structure. We begin with results concerning critical points and…

Probability · Mathematics 2026-01-23 Eliran Subag

In a region above the Almeida-Thouless line, where we are able to control the thermodynamic limit of the Sherrington-Kirkpatrick model and to prove replica symmetry, we show that the fluctuations of the overlaps and of the free energy are…

Disordered Systems and Neural Networks · Physics 2009-11-07 Francesco Guerra , Fabio L. Toninelli

A mathematical model is developed, to jointly analyze elastic and inelastic scattering data of fluctuating membranes within a single theoretical framework. The model builds on a non-homogeneously clipped time-dependent Gaussian random…

In this review article, we discuss connections between the physics of disordered systems, phase transitions in inference problems, and computational hardness. We introduce two models representing the behavior of glassy systems, the spiked…

Disordered Systems and Neural Networks · Physics 2022-12-07 David Gamarnik , Cristopher Moore , Lenka Zdeborová

The unprecedented predictive success of deep generative models in complex many-body systems, such as AlphaFold3, raises an epistemological question: do these networks merely memorize data distributions via high-dimensional interpolation, or…

Disordered Systems and Neural Networks · Physics 2026-05-18 Wenjie Xi , Wei-Qiang Chen

General results from statistical learning theory suggest to understand not only brain computations, but also brain plasticity as probabilistic inference. But a model for that has been missing. We propose that inherently stochastic features…

Neural and Evolutionary Computing · Computer Science 2016-02-17 David Kappel , Stefan Habenschuss , Robert Legenstein , Wolfgang Maass
‹ Prev 1 4 5 6 7 8 10 Next ›