activity
20242026
collaborators
Showing 2024Show all

5 papers · 1 filter

cond-mat.dis-nn2024

Generalized hetero-associative neural networks

Elena Agliari, Andrea Alessandrelli, Adriano Barra +2

Auto-associative neural networks (e.g., the Hopfield model implementing the standard Hebbian prescription) serve as a foundational framework for pattern recognition and associative…

cond-mat.dis-nn2024

The thermodynamic limit in mean field neural networks

Elena Agliari, Adriano Barra, Pierluigi Bianco +2

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 studie…

cond-mat.dis-nn2024

Guerra interpolation for place cells

Martino Salomone Centonze, Alessandro Treves, Elena Agliari +1

Pyramidal cells that emit spikes when the animal is at specific locations of the environment are known as "place cells": these neurons are thought to provide an internal representa…

physics.bio-ph2024

Inverse modeling of time-delayed interactions via the dynamic-entropy formalism

Elena Agliari, Francesco Alemanno, Adriano Barra +3

Although instantaneous interactions are unphysical, a large variety of maximum entropy statistical inference methods match the model-inferred and the empirically-measured equal-tim…

cond-mat.dis-nn2024

Fundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines

Alberto Fachechi, Elena Agliari, Miriam Aquaro +2

We consider restricted Boltzmann machines with a binary visible layer and a Gaussian hidden layer trained by an unlabelled dataset composed of noisy realizations of a single ground…