11 papers
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…
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…
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…