New Hopfield networks part8(Machine Learning 2024)

Minimum Description Length Hopfield Networks

Authors: Matan Abudy, Nur Lan, Emmanuel Chemla, Roni Katzir

Abstract: Associative memory architectures are designed for memorization but also offer, through their retrieval method, a form of generalization to unseen inputs: stored memories can be seen as prototypes from this point of view. Focusing on Modern Hopfield Networks (MHN), we show that a large memorization capacity undermines the generalization opportunity. We offer a solution to better optimize this tradeoff. It relies on Minimum Description Length (MDL) to determine during training which memories to store, as well as how many of them.