# Minimum Description Length Hopfield Networks

arXiv: https://arxiv.org/abs/2311.06518 · HTML: https://mlsanity.com/paper/2311.06518/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 20 references that are in the map.
- First posted on arXiv 11 Nov 2023.

## Builds on (most cited first, 3 of 3)

- [Weight Agnostic Neural Networks](https://mlsanity.com/paper/1906.04358/) (2019)
- [Minimum Description Length Recurrent Neural Networks](https://mlsanity.com/paper/2111.00600/) (2021)
- [Benchmarking Neural Network Generalization for Grammar Induction](https://mlsanity.com/paper/2308.08253/) (2023)

## Built on by (most cited first, 1 of 1)

- [A Minimum Description Length Approach to Regularization in Neural Networks](https://mlsanity.com/paper/2505.13398/) (2025)

## Abstract (arXiv)

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.