21 citations · 69 across the 17 of their papers we have counts for
19 papers
Dense auto-hetero associative memories applied to noisy communication channels
Elena Agliari, Andrea Alessandrelli, Adriano Barra +1
Networks of interacting Hebbian networks have recently been shown to perform a task beyond associative memory, namely \emph{pattern disentanglement}: when fed with a spurious mixtu…
Partial annealing and pattern decorrelation in associative neural networks
Linda Albanese, Andrea Alessandrelli, Adriano Barra +2
Using the Hopfield model as a benchmark case, the present work focuses on the investigation of partially annealed associative neural networks, wherein neural dynamics is coupled to…
Dense Associative Memory with biased patterns: a Replica Symmetric analysis
Linda Albanese, Andrea Alessandrelli, Federico Carella
We investigate dense higher-order associative memories in the high storage regime when the stored patterns are biased, namely when the entries of the patterns are not symmetrically…
A Federated Many-to-One Hopfield model for associative Neural Networks
Andrea Alessandrelli, Fabrizio Durante, Andrea Ladiana +1
Federated learning enables collaborative training without sharing raw data, but struggles under client heterogeneity and streaming distribution shifts, where drift and novel data c…
Serial vs parallel recall in the Blume-Every-Griffiths neural networks
Linda Albanese, Andrea Alessandrelli, Adriano Barra +1
Fully connected Blume-Emery-Griffiths neural networks performing pattern recognition and associative memory have been heuristically studied in the past (mainly via the replica tric…
Yet another exponential Hopfield model
Linda Albanese, Andrea Alessandrelli, Adriano Barra +1
We propose and analyze a new variation of the so-called {\em exponential Hopfield model}, a recently introduced family of associative neural networks with unprecedented storage cap…
Supervised and Unsupervised protocols for hetero-associative neural networks
Andrea Alessandrelli, Adriano Barra, Andrea Ladiana +2
This paper introduces a learning framework for Three-Directional Associative Memory (TAM) models, extending the classical Hebbian paradigm to both supervised and unsupervised proto…
Multi-channel pattern reconstruction through -directional associative memories
Elena Agliari, Andrea Alessandrelli, Paulo Duarte Mourao +1
We consider -directional associative memories, composed of Hopfield networks, displaying imitative Hebbian intra-network interactions and anti-imitative Hebbian inter-networ…
Beyond Disorder: Unveiling Cooperativeness in Multidirectional Associative Memories
Andrea Alessandrelli, Adriano Barra, Andrea Ladiana +2
By leveraging tools from the statistical mechanics of complex systems, in these short notes we extend the architecture of a neural network for hetero-associative memory (called thr…
Networks of neural networks: more is different
Elena Agliari, Andrea Alessandrelli, Adriano Barra +2
The common thread behind the recent Nobel Prize in Physics to John Hopfield and those conferred to Giorgio Parisi in 2021 and Philip Anderson in 1977 is disorder. Quoting Philip An…
Boolean SK Model
Linda Albanese, Andrea Alessandrelli
For over half a century, statistical mechanics of spin glasses played as a paradigm to model and interpret disparate phenomena, ranging from quantitative biology to computer scienc…
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…
Unsupervised and Supervised learning by Dense Associative Memory under replica symmetry breaking
Linda Albanese, Andrea Alessandrelli, Alessia Annibale +1
Statistical mechanics of spin glasses is one of the main strands toward a comprehension of information processing by neural networks and learning machines. Tackling this approach,…
Parallel Learning by Multitasking Neural Networks
Elena Agliari, Andrea Alessandrelli, Adriano Barra +1
A modern challenge of Artificial Intelligence is learning multiple patterns at once (i.e.parallel learning). While this can not be accomplished by standard Hebbian associative neur…
About the de Almeida-Thouless line in neural networks
Linda Albanese, Andrea Alessandrelli, Adriano Barra +1
In this work we present a rigorous and straightforward method to detect the onset of the instability of replica-symmetric theories in information processing systems, which does not…
Dense Hebbian neural networks: a replica symmetric picture of supervised learning
Elena Agliari, Linda Albanese, Francesco Alemanno +5
We consider dense, associative neural-networks trained by a teacher (i.e., with supervision) and we investigate their computational capabilities analytically, via statistical-mecha…
Dense Hebbian neural networks: a replica symmetric picture of unsupervised learning
Elena Agliari, Linda Albanese, Francesco Alemanno +5
We consider dense, associative neural-networks trained with no supervision and we investigate their computational capabilities analytically, via a statistical-mechanics approach, a…
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…
Rigorous approaches for spin glass and Gaussian spin glass with P-wise interactions
Linda Albanese, Andrea Alessandrelli
Purpose of this paper is to face up to P-spin glass and Gaussian P-spin model, i.e. spin glasses with polynomial interactions of degree P > 2. We consider the replica symmetry and…