no code implementations • 9 Aug 2023 • Marco Benedetti, Louis Carillo, Enzo Marinari, Marc Mèzard
Among the performance-enhancing procedures for Hopfield-type networks that implement associative memory, Hebbian Unlearning (or dreaming) strikes for its simplicity and its clear biological interpretation.
no code implementations • 26 Feb 2023 • Marco Benedetti, Enrico Ventura
We show how adding structure to noisy training data can substantially improve the algorithm performance, allowing the network to approach perfect retrieval of the memories and wide basins of attraction, even in the scenario of maximal injected noise.
no code implementations • 13 Jan 2021 • Marco Benedetti, Victor Dotsenko, Giulia Fischetti, Enzo Marinari, Gleb Oshanin
We study the recognition capabilities of the Hopfield model with auxiliary hidden layers, which emerge naturally upon a Hubbard-Stratonovich transformation.
Disordered Systems and Neural Networks Statistical Mechanics Biological Physics Neurons and Cognition
no code implementations • 21 Apr 2020 • Luigi Bellomarini, Marco Benedetti, Andrea Gentili, Rosario Laurendi, Davide Magnanimi, Antonio Muci, Emanuel Sallinger
In the COVID-19 outbreak, governments have applied progressive restrictions to production activities, permitting only those that are considered strategic or that provide essential services.