49 citations · 150 across the 13 of their papers we have counts for
14 papers
A polynomially accelerated fixed-point iteration for vector problems
Francesco Alemanno
Fixed-point solvers are ubiquitous in nonlinear PDEs, yet their progress collapses whenever the Jacobian at the solution carries an eigenvalue arbitrarily close to one. We ask whet…
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…
Regularization, early-stopping and dreaming: a Hopfield-like setup to address generalization and overfitting
Elena Agliari, Francesco Alemanno, Miriam Aquaro +1
In this work we approach attractor neural networks from a machine learning perspective: we look for optimal network parameters by applying a gradient descent over a regularized los…
Ultrametric identities in glassy models of Natural Evolution
Elena Agliari, Francesco Alemanno, Miriam Aquaro +1
Spin-glasses constitute a well-grounded framework for evolutionary models. Of particular interest for (some of) these models is the lack of self-averaging of their order parameters…
Hopfield model with planted patterns: a teacher-student self-supervised learning model
Francesco Alemanno, Luca Camanzi, Gianluca Manzan +1
While Hopfield networks are known as paradigmatic models for memory storage and retrieval, modern artificial intelligence systems mainly stand on the machine learning paradigm. We…
Supervised Hebbian Learning
Francesco Alemanno, Miriam Aquaro, Ido Kanter +2
In neural network's Literature, Hebbian learning traditionally refers to the procedure by which the Hopfield model and its generalizations store archetypes (i.e., definite patterns…
Replica symmetry breaking in dense neural networks
Linda Albanese, Francesco Alemanno, Andrea Alessandrelli +1
Understanding the glassy nature of neural networks is pivotal both for theoretical and computational advances in Machine Learning and Theoretical Artificial Intelligence. Keeping t…
The emergence of a concept in shallow neural networks
Elena Agliari, Francesco Alemanno, Adriano Barra +1
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…
Pattern recognition in Deep Boltzmann machines
Elena Agliari, Linda Albanese, Francesco Alemanno +1
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…
Interpolating between boolean and extremely high noisy patterns through Minimal Dense Associative Memories
Francesco Alemanno, Martino Centonze, Alberto Fachechi
Recently, Hopfield and Krotov introduced the concept of {\em dense associative memories} [DAM] (close to spin-glasses with -wise interactions in a disordered statistical mechani…
Neural networks with redundant representation: detecting the undetectable
Elena Agliari, Francesco Alemanno, Adriano Barra +2
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…
Generalized Guerra's interpolation schemes for dense associative neural networks
Elena Agliari, Francesco Alemanno, Adriano Barra +1
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 st…
Dreaming neural networks: rigorous results
Elena Agliari, Francesco Alemanno, Adriano Barra +1
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, du…
A novel derivation of the Marchenko-Pastur law through analog bipartite spin-glasses
Elena Agliari, Francesco Alemanno, Adriano Barra +1
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 we…