English

Memory Mosaics

Machine Learning 2025-03-03 v3 Artificial Intelligence Neural and Evolutionary Computing

Abstract

Memory Mosaics are networks of associative memories working in concert to achieve a prediction task of interest. Like transformers, memory mosaics possess compositional capabilities and in-context learning capabilities. Unlike transformers, memory mosaics achieve these capabilities in comparatively transparent way ("predictive disentanglement"). We illustrate these capabilities on a toy example and also show that memory mosaics perform as well or better than transformers on medium-scale language modeling tasks.

Keywords

Cite

@article{arxiv.2405.06394,
  title  = {Memory Mosaics},
  author = {Jianyu Zhang and Niklas Nolte and Ranajoy Sadhukhan and Beidi Chen and Léon Bottou},
  journal= {arXiv preprint arXiv:2405.06394},
  year   = {2025}
}
R2 v1 2026-06-28T16:23:06.533Z