Poster
in
Workshop: Associative Memory & Hopfield Networks in 2023
Minimum Description Length Hopfield Networks
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.
Chat is not available.