Eigenvector Dreaming

Author:

Marco Benedetti, Louis Carillo, Enzo Marinari, Marc Mèzard

Keyword:

Condensed Matter, Disordered Systems and Neural Networks, Disordered Systems and Neural Networks (cond-mat.dis-nn), Neural and Evolutionary Computing (cs.NE)

journal:

date:

2023-08-08 16:00:00

Abstract

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. Yet, it does not easily lend itself to a clear analytical understanding. Here we show how Hebbian Unlearning can be effectively described in terms of a simple evolution of the spectrum and the eigenvectors of the coupling matrix. We use these ideas to design new dreaming algorithms that are effective from a computational point of view, and are analytically far more transparent than the original scheme.

PDF: Eigenvector Dreaming.pdf