Elena Agliari

Elena Agliari
Sapienza University of Rome | la sapienza · Department of Mathematics "Guido Catelnuovo"

PhD

About

139
Publications
13,778
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,188
Citations
Introduction
My current interests are: - associative neural networks - first-passage phenomena in inhomogeneous structures - statistical mechanics of disordered systems - biological processing via reaction kinetics
Additional affiliations
June 2015 - present
Sapienza University of Rome
Position
  • Researcher
December 2010 - November 2013
Università di Parma
Position
  • Research Associate
December 2010 - November 2013
Università di Parma
Position
  • Researcher

Publications

Publications (139)
Preprint
Full-text available
As well known, Hebb's learning traces its origin in Pavlov's Classical Conditioning, however, while the former has been extensively modelled in the past decades (e.g., by Hopfield model and countless variations on theme), as for the latter modelling has remained largely unaddressed so far; further, a bridge between these two pillars is totally lack...
Article
Inspired by a formal equivalence between the Hopfield model and restricted Boltzmann machines (RBMs), we design a Boltzmann machine, referred to as the dreaming Boltzmann machine (DBM), which achieves better performances than the standard one. The novelty in our model lies in a precise prescription for intralayer connections among hidden neurons wh...
Preprint
Full-text available
The gap between the huge volumes of data needed to train artificial neural networks and the relatively small amount of data needed by their biological counterparts is a central puzzle in machine learning. Here, inspired by biological information-processing, we introduce a generalized Hopfield network where pairwise couplings between neurons are bui...
Article
Full-text available
We consider restricted Boltzmann machine (RBMs) trained over an unstructured dataset made of blurred copies of definite but unavailable “archetypes” and we show that there exists a critical sample size beyond which the RBM can learn archetypes, namely the machine can successfully play as a generative model or as a classifier, according to the opera...
Preprint
Dense associative memories (DAM), are widespread models in artificial intelligence used for pattern recognition tasks; computationally, they have been proven to be robust against adversarial input and theoretically, leveraging their analogy with spin-glass systems, they are usually treated by means of statistical-mechanics tools. Here we develop an...
Preprint
Full-text available
In neural network's Literature, {\em Hebbian learning} traditionally refers to the procedure by which the Hopfield model and its generalizations {\em store} archetypes (i.e., definite patterns that are experienced just once to form the synaptic matrix). However, the term {\em learning} in Machine Learning refers to the ability of the machine to ext...
Article
The formal equivalence between the Hopfield network (HN) and the Boltzmann Machine (BM) has been well established in the context of random, unstructured and unbiased patterns to be retrieved and recognised. Here we extend this equivalence to the case of “biased” patterns, that is patterns which display an unbalanced count of positive neurons/pixels...
Article
We consider a multi-layer Sherrington-Kirkpatrick spin-glass as a model for deep restricted Boltzmann machines with quenched random weights and solve for its free energy in the thermodynamic limit by means of Guerra's interpolating techniques under the RS and 1RSB ansatz. In particular, we recover the expression already known for the replica-symmet...
Article
Full-text available
We consider a three-layer restricted Boltzmann machine, where the two visible layers (encoding for input and output, respectively) are made of binary neurons while the hidden layer is made of Gaussian neurons, and we show a formal equivalence with a Hopfield model. The machine architecture allows for different learning and operational modes: when a...
Preprint
Full-text available
We consider restricted Boltzmann machine (RBMs) trained over an unstructured dataset made of blurred copies of definite but unavailable ``archetypes'' and we show that there exists a critical sample size beyond which the RBM can learn archetypes, namely the machine can successfully play as a generative model or as a classifier, according to the ope...
Preprint
We consider a multi-layer Sherrington-Kirkpatrick spin-glass as a model for deep restricted Boltzmann machines and we solve for its quenched free energy, in the thermodynamic limit and allowing for a first step of replica symmetry breaking. This result is accomplished rigorously exploiting interpolating techniques and recovering the expression alre...
Article
Restricted Boltzmann machines (RBMs) with a binary visible layer of size N and a Gaussian hidden layer of size P have been proved to be equivalent to a Hopfield neural network (HNN) made of N binary neurons and storing P patterns ξ, as long as the weights w in the former are identified with the patterns. Here we aim to leverage this equivalence to...
Preprint
In this work we introduce and investigate the properties of the "relativistic" Hopfield model endowed with temporally correlated patterns. First, we review the "relativistic" Hopfield model and we briefly describe the experimental evidence underlying correlation among patterns. Then, we face the study of the resulting model exploiting statistical-m...
Article
Full-text available
The Hopfield model and the Boltzmann machine are among the most popular examples of neural networks. The latter, widely used for classification and feature detection, is able to efficiently learn a generative model from observed data and constitutes the benchmark for statistical learning. The former, designed to mimic the retrieval phase of an arti...
Article
In this work, we introduce and investigate the properties of the “relativistic” Hopfield model endowed with temporally correlated patterns. First, we review the “relativistic” Hopfield model and we briefly describe the experimental evidence underlying correlation among patterns. Then, we face the study of the resulting model exploiting statistical-...
Article
Full-text available
The retrieval capabilities of associative neural networks are known to be impaired by fast noise, which endows neuron behavior with some degree of stochasticity, and by slow noise, due to interference among stored memories; here, we allow for another source of noise, referred to as “synaptic noise,” which may stem from i. corrupted information prov...
Article
Full-text available
In this work we apply statistical mechanics tools to infer cardiac pathologies over a sample of M patients whose heart rate variability has been recorded via 24 h Holter device and that are divided in different classes according to their clinical status (providing a repository of labelled data). Considering the set of inter-beat interval sequences...
Preprint
The retrieval capabilities of associative neural networks can be impaired by different kinds of noise: the fast noise (which makes neurons more prone to failure), the slow noise (stemming from interference among stored memories), and synaptic noise (due to possible flaws during the learning or the storing stage). In this work we consider dense asso...
Article
Full-text available
In this paper we develop statistical algorithms to infer possible cardiac pathologies, based on data collected from 24 h Holter recording over a sample of 2829 labelled patients; labels highlight whether a patient is suffering from cardiac pathologies. In the first part of the work we analyze statistically the heart-beat series associated to each p...
Preprint
Full-text available
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) in order to work also with the Hopfield model (i.e., a pairwise mean-field neural-network whose couplings are...
Article
Full-text available
In this work we develop analytical techniques to investigate a broad class of associative neural networks set in the high-storage regime. These techniques translate the original statistical–mechanical problem into an analytical-mechanical one which implies solving a set of partial differential equations, rather than tackling the canonical probabili...
Article
Full-text available
Migration of cells can be characterized by two prototypical types of motion: individual and collective migration. We propose a statistical inference approach designed to detect the presence of cell-cell interactions that give rise to collective behaviors in cell motility experiments. This inference method has been first successfully tested on synth...
Article
Full-text available
We consider a three-layer Sejnowski machine and show that features learnt via contrastive divergence have a dual representation as patterns in a dense associative memory of order P=4. The latter is known to be able to Hebbian store an amount of patterns scaling as N^(P−1), where N denotes the number of constituting binary neurons interacting P wise...
Article
We consider two random walkers embedded in a finite, two-dimension comb and we study the mean first-encounter time (MFET) evidencing (mainly numerically) different scalings with the linear size of the underlying network according to the initial position of the walkers. If one of the two players is not allowed to move, then the first-encounter probl...
Preprint
Migration of cells can be characterized by two, prototypical types of motion: individual and collective migration. We propose a statistical-inference approach designed to detect the presence of cell-cell interactions that give rise to collective behaviors in cell-motility experiments. Such inference method has been first successfully tested on synt...
Preprint
Full-text available
We consider a three-layer Sejnowski machine and show that features learnt via contrastive divergence have a dual representation as patterns in a dense associative memory of order P=4. The latter is known to be able to Hebbian-store an amount of patterns scaling as N^{P-1}, where N denotes the number of constituting binary neurons interacting P-wise...
Preprint
Full-text available
In this work we develop analytical techniques to address, in the high-storage regime, phase diagrams for a broad class of neural networks (whose cost functions may include various, polynomial, contributions both in the neurons and the patterns, hence {\em dense}). The techniques translate the original statistical-mechanical problem into a pure anal...
Article
Full-text available
The standard Hopfield model for associative neural networks accounts for biological Hebbian learning and acts as the harmonic oscillator for pattern recognition, however its maximal storage capacity is α∼0.14, far from the theoretical bound for symmetric networks, i.e. α=1. Inspired by sleeping and dreaming mechanisms in mammal brains, we propose a...
Article
Full-text available
Restricted Boltzmann machines (RBMs) constitute one of the main models for machine statistical inference and they are widely employed in artificial intelligence as powerful tools for (deep) learning. However, in contrast with countless remarkable practical successes, their mathematical formalization has been largely elusive: from a statistical-mech...
Article
The relativistic Hopfield model constitutes a generalization of the standard Hopfield model that is derived by the formal analogy between the statistical-mechanic framework embedding neural networks and the Lagrangian mechanics describing a fictitious single-particle motion in the space of the tuneable parameters of the network itself. In this anal...
Article
In this work, we consider a class of recursively grown fractal networks Gn(t) whose topology is controlled by two integer parameters, t and n. We first analyse the structural properties of Gn(t) (including fractal dimension, modularity, and clustering coefficient), and then we move to its transport properties. The latter are studied in terms of fir...
Preprint
Full-text available
Recently a daily routine for associative neural networks has been proposed: the network Hebbian-learns during the awake state (thus behaving as a standard Hopfield model), then, during its sleep state, optimizing information storage, it consolidates pure patterns and removes spurious ones: this forces the synaptic matrix to collapse to the projecto...
Preprint
Full-text available
In this work we consider the {\em analog bipartite spin-glass} (or {\em real-valued restricted Boltzmann machine} in a neural network jargon), whose variables (those quenched as well as those dynamical) share standard Gaussian distributions. First, via Guerra's interpolation technique, we express its quenched free energy in terms of the natural ord...
Preprint
Full-text available
The standard Hopfield model for associative neural networks accounts for biological Hebbian learning and acts as the harmonic oscillator for pattern recognition, however its maximal storage capacity is $\alpha \sim 0.14$, far from the theoretical bound for symmetric networks, i.e. $\alpha =1$. Inspired by sleeping and dreaming mechanisms in mammal...
Preprint
Full-text available
The relativistic Hopfield model constitutes a generalization of the standard Hopfield model that is derived by the formal analogy between the statistical-mechanic framework embedding neural networks and the Lagrangian mechanics describing a fictitious single-particle motion in the space of the tuneable parameters of the network itself. In this anal...
Preprint
Full-text available
Restricted Boltzmann machines (RBMs) constitute one of the main models for machine statistical inference and they are widely employed in Artificial Intelligence as powerful tools for (deep) learning. However, in contrast with countless remarkable practical successes, their mathematical formalization has been largely elusive: from a statistical-mech...
Article
Full-text available
In this work we introduce a multi-species generalization of the Hopfield model for associative memory, where neurons are divided into groups and both inter-groups and intra-groups pair-wise interactions are considered, with different intensities. Thus, this system contains two of the main ingredients of modern deep neural-network architectures: Heb...
Article
Full-text available
In recent years Italy has been involved in massive migration flows and, consequently, migrant integration is becoming a urgent political, economic and social issue. In this paper we apply quantitative methods, based on probability theory and statistical mechanics, to study the relative integration of migrants in Italy. In particular, we focus on th...
Article
Full-text available
Urban and peri-urban forests are green infrastructures (GI) that play a substantial role in delivering ecosystem services such as the amelioration of air quality by the removal of air pollutants, among which is ozone (O3), which is the most harmful pollutant in Mediterranean metropolitan areas. Models may provide a reliable estimate of gas exchange...
Article
Full-text available
Complex biochemical pathways or regulatory enzyme kinetics can be reduced to chains of elementary reactions, which can be described in terms of chemical kinetics. This discipline provides a set of tools for quantifying and understanding the dialogue between reactants, whose framing into a solid and consistent mathematical description is of pivotal...
Article
Full-text available
We consider the Maki-Thompson model for the stochastic propagation of a rumour within a population. In this model the population is made up of “spreaders”, “ignorants” and “stiflers”; any spreader attempts to pass the rumour to the other individuals via pair-wise interactions and in case the other individual is an ignorant, it becomes a spreader, w...
Article
Full-text available
In this paper we discuss the applicability of numerical descriptors and statistical physics concepts to characterize complex biological systems observed at microscopic level through organ on chip approach. To this end, we employ data collected on a microfluidic platform in which leukocytes can move through suitably built channels toward their targe...
Article
Full-text available
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 associative memory. In this equivalence, weights in the former play as patterns in the latter. As Boltzmann machines...
Article
Full-text available
Fractal (or transfractal) features are common in real-life networks and are known to influence the dynamic processes taking place in the network itself. Here, we consider a class of scale-free deterministic networks, called (u, v)-flowers, whose topological properties can be controlled by tuning the parameters u and v; in particular, for u>1, they...
Article
Full-text available
Interactions between natives and foreign-born individuals may help to stimulate the development and the diversification of bilateral trade relationships. In fact, migrants act as trade facilitators reducing transaction costs in export activities and, consequently, more local firms are able to establish new trade relationships abroad. The pro-trade...
Article
Full-text available
Encounters between walkers performing a random motion on an appropriate structure can describe a wide variety of natural phenomena ranging from pharmacokinetics to foraging. On homogeneous structures the asymptotic encounter probability between two walkers is (qualitatively) independent of whether both walkers are moving or one is kept fixed. On in...
Article
Full-text available
Statistical mechanics provides an effective framework to investigate information processing in biochemical reactions. Within such framework far-reaching analogies are established among (anti-)cooperative collective behaviors} in chemical kinetics, (anti-)ferromagnetic spin models in statistical mechanics and operational amplifiers/flip-flops in cyb...
Article
Full-text available
We consider the Dyson hierarchical graph $\mathcal{G}$, that is a weighted fully-connected graph, where the pattern of weights is ruled by the parameter $\sigma \in (1/2, 1]$. Exploiting the deterministic recursivity through which $\mathcal{G}$ is built, we are able to derive explicitly the whole set of the eigenvalues and the eigenvectors for its...
Article
In this paper we study Markov processes and related first-passage problems on a class of weighted, modular graphs which generalize the Dyson hierarchical model. In these networks, the coupling strength between two nodes depends on their distance and is modulated by a parameter σ. We find that, in the thermodynamic limit, ergodicity is lost and the...
Article
Full-text available
In this work we apply techniques and modus operandi typical of Statistical Mechanics to a large dataset about key social quantifiers and compare the resulting behaviors of five European nations, namely France, Germany, Italy, Spain and Switzerland. The social quantifiers considered are i. the evolution of the number of autochthonous marriages (i.e....
Article
Full-text available
We consider a particle performing a stochastic motion on a one-dimensional lattice with jump lengths distributed according to a power law with exponent $\mu+1$. Assuming that the walker moves in the presence of a distribution $a(x)$ of targets (traps) depending on the spatial coordinate $x$, we study the probability that the walker will eventually...
Article
The best strategy to immunize a complex network is usually evaluated in terms of the percolation threshold, i.e. the number of vaccine doses which make the largest connected cluster (LCC) vanish. The strategy inducing the minimum percolation threshold represents the optimal way to immunize the network. Here we show that the efficacy of the immuniza...
Article
Full-text available
The best strategy to immunize a complex network is usually evaluated in terms of the percolation threshold, i.e. the number of vaccine doses which make the largest connected cluster (LCC) vanish. The strategy inducing the minimum percolation threshold represents the optimal way to immunize the network. Here we show that the efficacy of the immuniza...
Article
Full-text available
In this paper, we consider discrete time random walks on the pseudofractal scale-free web (PSFW) and we study analytically the related first passage properties. First, we classify the nodes of the PSFW into different levels and propose a method to derive the generation function of the first passage probability from an arbitrary starting node to the...
Article
Full-text available
Hierarchical networks are attracting a renewal interest for modelling the organization of a number of biological systems and for tackling the complexity of statistical mechanical models beyond mean-field limitations. Here we consider the Dyson hierarchical construction for ferromagnets, neural networks and spin-glasses, recently analyzed from a sta...