English
Related papers

Related papers: Jamming in multilayer supervised learning models

200 papers

We study a well known machine learning model -the perceptron- as a simple model of jamming of hard objects. We exhibit two regimes: 1) a convex optimisation regime where jamming is hypostatic and non-critical. 2) a non convex optimisation…

Statistical Mechanics · Physics 2016-03-08 Silvio Franz , Giorgio Parisi

In this Letter, we analyze the quantum dynamics of the perceptron model: a particle is constrained on a $N$-dimensional sphere, with $N\to \infty$, and subjected to a set of randomly placed hard-wall potentials. This model has several…

Disordered Systems and Neural Networks · Physics 2021-05-05 Claudia Artiaco , Federico Balducci , Giorgio Parisi , Antonello Scardicchio

Recent computer simulations have uncovered the striking difference between the jamming transition of spherical and non-spherical particles. While systems of spherical particles are isostatic at the jamming point, systems of nonspherical…

Disordered Systems and Neural Networks · Physics 2019-08-29 Harukuni Ikeda , Pierfrancesco Urbani , Francesco Zamponi

Random constraint satisfaction problems (CSP) have been studied extensively using statistical physics techniques. They provide a benchmark to study average case scenarios instead of the worst case one. The interplay between statistical…

Disordered Systems and Neural Networks · Physics 2017-06-06 Silvio Franz , Giorgio Parisi , Maksim Sevelev , Pierfrancesco Urbani , Francesco Zamponi

Gradient descent dynamics in complex energy landscapes, i.e. featuring multiple minima, finds application in many different problems, from soft matter to machine learning. Here, we analyze one of the simplest examples, namely that of soft…

Statistical Mechanics · Physics 2022-08-23 Alessandro Manacorda , Francesco Zamponi

Criticality in statistical physics naturally emerges at isolated points in the phase diagram. Jamming of spheres is not an exception: varying density, it is the critical point that separates the unjammed phase where spheres do not overlap…

Disordered Systems and Neural Networks · Physics 2019-09-18 Silvio Franz , Antonio Sclocchi , Pierfrancesco Urbani

Deep neural networks (DNN) with a huge number of adjustable parameters remain largely black boxes. To shed light on the hidden layers of DNN, we study supervised learning by a DNN of width $N$ and depth $L$ consisting of $NL$ perceptrons…

Disordered Systems and Neural Networks · Physics 2023-08-01 Hajime Yoshino

The jamming transition is ubiquitous. It is present in granular matter, colloids, glasses, and many other systems. Yet, it defines a critical point whose properties still need to be fully understood. A major breakthrough came about when the…

Soft Condensed Matter · Physics 2023-09-11 Claudia Artiaco , Rafael Díaz Hernández Rojas , Giorgio Parisi , Federico Ricci-Tersenghi

Amorphous packings of non-spherical particles such as ellipsoids and spherocylinders are known to be hypostatic: the number of mechanical contacts between particles is smaller than the number of degrees of freedom, thus violating Maxwell's…

Disordered Systems and Neural Networks · Physics 2018-11-21 Carolina Brito , Harukuni Ikeda , Pierfrancesco Urbani , Matthieu Wyart , Francesco Zamponi

The concept of jamming has attracted great research interest due to its broad relevance in soft matter such as liquids, glasses, colloids, foams, and granular materials, and its deep connection to the sphere packing problem and optimization…

Soft Condensed Matter · Physics 2021-04-07 Yuliang Jin , Hajime Yoshino

The jamming transition of particles with finite-range interactions is characterized by a variety of critical phenomena, including power law distributions of marginal contacts. We numerically study a recently proposed simple model of…

Statistical Mechanics · Physics 2016-01-20 Yoav Kallus

Recurrent neural networks (RNNs) notoriously struggle to learn long-term memories, primarily due to vanishing and exploding gradients. The recent success of state-space models (SSMs), a subclass of RNNs, to overcome such difficulties…

Machine Learning · Computer Science 2024-11-06 Nicolas Zucchet , Antonio Orvieto

The discontinuous jump in the bulk modulus $B$ at the jamming transition is a consequence of the formation of a critical contact network of spheres that resists compression. We introduce lattice models with underlying under-coordinated…

Soft Condensed Matter · Physics 2019-04-03 Danilo B. Liarte , Xiaoming Mao , Olaf Stenull , T. C. Lubensky

We present a parallel derivation of the Thouless-Anderson-Palmer (TAP) equations and of an effective potential for the negative perceptron and soft sphere models in high dimension. Both models are continuous constrained satisfaction…

Disordered Systems and Neural Networks · Physics 2016-09-21 Ada Altieri , Silvio Franz , Giorgio Parisi

This paper develops a neural jamming phase diagram that interprets the emergence of consciousness in large language models as a critical phenomenon in high-dimensional disordered systems.By establishing analogies with jamming transitions in…

Disordered Systems and Neural Networks · Physics 2025-07-14 Kaichen Ouyang

We report an analytical study of the vibrational spectrum of the simplest model of jamming, the soft perceptron. We identify two distinct classes of soft modes. The first kind of modes are related to isostaticity and appear only in the…

Disordered Systems and Neural Networks · Physics 2015-11-30 Silvio Franz , Giorgio Parisi , Pierfrancesco Urbani , Francesco Zamponi

We numerically study the jamming transition of frictionless polydisperse spheres in three dimensions. We use an efficient thermalisation algorithm for the equilibrium hard sphere fluid and generate amorphous jammed packings over a range of…

Statistical Mechanics · Physics 2017-10-16 Misaki Ozawa , Ludovic Berthier , Daniele Coslovich

One of the most influential results in neural network theory is the universal approximation theorem [1, 2, 3] which states that continuous functions can be approximated to within arbitrary accuracy by single-hidden-layer feedforward neural…

Machine Learning · Computer Science 2021-12-16 Clemens Hutter , Recep Gül , Helmut Bölcskei

Jamming criticality defines a universality class that includes systems as diverse as glasses, colloids, foams, amorphous solids, constraint satisfaction problems, neural networks, etc. A particularly interesting feature of this class is…

We outline the general framework of machine learning (ML) methods for multi-scale dynamical modeling of condensed matter systems, and in particular of strongly correlated electron models. Complex spatial temporal behaviors in these systems…

Strongly Correlated Electrons · Physics 2022-01-06 Puhan Zhang , Sheng Zhang , Gia-Wei Chern
‹ Prev 1 2 3 10 Next ›