Back to Search Start Over

Daydreaming Hopfield Networks and their surprising effectiveness on correlated data

Authors :
Serricchio, Ludovica
Bocchi, Dario
Chilin, Claudio
Marino, Raffaele
Negri, Matteo
Cammarota, Chiara
Ricci-Tersenghi, Federico
Publication Year :
2024

Abstract

To improve the storage capacity of the Hopfield model, we develop a version of the dreaming algorithm that perpetually reinforces the patterns to be stored (as in the Hebb rule), and erases the spurious memories (as in dreaming algorithms). For this reason, we called it Daydreaming. Daydreaming is not destructive and it converges asymptotically to stationary retrieval maps. When trained on random uncorrelated examples, the model shows optimal performance in terms of the size of the basins of attraction of stored examples and the quality of reconstruction. We also train the Daydreaming algorithm on correlated data obtained via the random-features model and argue that it spontaneously exploits the correlations thus increasing even further the storage capacity and the size of the basins of attraction. Moreover, the Daydreaming algorithm is also able to stabilize the features hidden in the data. Finally, we test Daydreaming on the MNIST dataset and show that it still works surprisingly well, producing attractors that are close to unseen examples and class prototypes.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2405.08777
Document Type :
Working Paper