Speaker
Description
To improve the storage capacity of the Hopfield model, we develop a version of the dreaming al-
gorithm 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. Day-
dreaming 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 stabi-
lize 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.
