Minimum Description Length Hopfield Networks
Machine Learning
2023-11-14 v1 Computation and Language
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.
Keywords
Cite
@article{arxiv.2311.06518,
title = {Minimum Description Length Hopfield Networks},
author = {Matan Abudy and Nur Lan and Emmanuel Chemla and Roni Katzir},
journal= {arXiv preprint arXiv:2311.06518},
year = {2023}
}
Comments
4 pages, Associative Memory & Hopfield Networks Workshop at NeurIPS2023