English
Related papers

Related papers: Beyond storage capacity in a single model neuron: …

200 papers

In this paper we discuss a disordered $d$-dimensional Euclidean $\lambda\varphi^{4}$ model. The dominant contribution to the average free energy of this system is written as a series of the replica partition functions of the model. In each…

High Energy Physics - Theory · Physics 2017-09-20 R. Acosta Diaz , G. Menezes , N. F. Svaiter , C. A. D. Zarro

Neural networks are able to extract information from the timing of spikes. Here we provide new results on the behavior of the simplest neuronal model which is able to decode information embedded in temporal spike patterns, the so called…

Disordered Systems and Neural Networks · Physics 2015-06-17 Carlo Baldassi , Alfredo Braunstein , Riccardo Zecchina

The Sherrington-Kirkpatrick spin glass model has been studied as a source of insight into the statistical mechanics of systems with highly diversified collections of competing low energy states. The goal of this summary is to present some…

Mathematical Physics · Physics 2008-09-29 Michael Aizenman , Robert Sims , Shannon L. Starr

By defining a spatially varying replica overlap parameter for a supercooled liquid referenced to an ensemble of fiducial liquid state configurations we explicitly construct a constrained replica free energy functional that maps directly…

Soft Condensed Matter · Physics 2009-11-13 Jacob D. Stevenson , Aleksandra M. Walczak , Randall W. Hall , Peter G. Wolynes

We illustrate how computer-aided methods can be used to investigate the fundamental limits of the caching systems, which are significantly different from the conventional analytical approach usually seen in the information theory…

Information Theory · Computer Science 2018-08-28 Chao Tian

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

We study the computational capacity of a model neuron, the Tempotron, which classifies sequences of spikes by linear-threshold operations. We use statistical mechanics and extreme value theory to derive the capacity of the system in random…

Neurons and Cognition · Quantitative Biology 2010-11-30 Ran Rubin , Remi Monasson , Haim Sompolinsky

In this paper we study the bipartite version of Sherrington-Kirkpatrick model. We prove that the free energy density is given by an analogue of the Parisi formula, that contains both the usual overlap and an additional new type of overlap.…

Disordered Systems and Neural Networks · Physics 2018-12-18 Liming Pan , Simone Franchini

Quenched disorder is very important but notoriously hard. In 1979, Parisi and Sourlas proposed an interesting and powerful conjecture about the infrared fixed points with random field type of disorder: such fixed points should possess an…

High Energy Physics - Theory · Physics 2020-05-20 Apratim Kaviraj , Slava Rychkov , Emilio Trevisani

In order to study certain questions concerning the distribution of the overlap in Sherrington--Kirkpatrick type models, such as the chaos and ultrametricity problems, it seems natural to study the free energy of multiple systems with…

Probability · Mathematics 2009-09-29 Dmitry Panchenko , Michel Talagrand

A comprehensive review will be given about the rich mathematical structure of mean field spin glass theory, mostly developed, until now, in the frame of the methods of theoretical physics, based on deep physical intuition and hints coming…

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

We explore the consequences of Replica Symmetry Breaking at zero temperature. We introduce a repulsive coupling between a system and its unperturbed ground state. In the Replica Symmetry Breaking scenario a finite coupling induces a non…

Disordered Systems and Neural Networks · Physics 2013-04-30 Silvio Franz , Giorgio Parisi

Replica-mean-field models have been proposed to decipher the activity of neural networks via a multiply-and-conquer approach. In this approach, one considers limit networks made of infinitely many replicas with the same basic neural…

Probability · Mathematics 2020-04-15 François Baccelli , Thibaud Taillefumier

We here study whether training biases can make hidden neurons specialize in minimal one-hidden-layer MLPs, and whether such specialization improves prototype-based reconstruction of the training dataset from the learned weights. We consider…

Machine Learning · Computer Science 2026-05-26 Enrique Alba , Ezequiel Lopez-Rubio

We prove that the Parisi measure of the mixed p-spin model at zero temperature has infinitely many points in its support. This establishes Parisi's prediction that the functional order parameter of the Sherrington-Kirkpatrick model is not a…

Probability · Mathematics 2021-06-18 Antonio Auffinger , Wei-Kuo Chen , Qiang Zeng

Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network…

Neurons and Cognition · Quantitative Biology 2016-02-17 Alireza Alemi , Carlo Baldassi , Nicolas Brunel , Riccardo Zecchina

We start with a rather detailed, general discussion of recent results of the replica approach to statistical mechanics of a single classical particle placed in a random $N (\gg 1)$-dimensional Gaussian landscape and confined by a…

Disordered Systems and Neural Networks · Physics 2008-01-03 Yan V Fyodorov , Ian Williams

Synchronization of two replicas of coupled map lattices for continuous maps is known to be in the multiplicative noise universality class. We study this transition in the presence of quenched disorder in coupling. The disorder is identical…

Statistical Mechanics · Physics 2023-11-02 Naval R. Sabe , Priyanka D. Bhoyar , Prashant M. Gade

We consider the quadrupolar glass model with infinite-range random interaction. Introducing a simple one-step replica symmetry breaking ansatz we investigate the para-glass continuous (discontinuous) transition which occurs below (above) a…

Disordered Systems and Neural Networks · Physics 2007-05-23 F. P. Mancini , D. Sherrington

We argue that when the number of spins $N$ in the SK model is finite, the Parisi scheme can be terminated after $K$ replica-symmetry breaking steps, where $K(N) \propto N^{1/6}$. We have checked this idea by Monte Carlo simulations: we…

Disordered Systems and Neural Networks · Physics 2009-11-13 T. Aspelmeier , A. Billoire , E. Marinari , M. A. Moore