Sequential Pattern Retrieval: New Representations Inspired by Non-Equilibrium Physics and Associative Memory Models

Abstract

Generating a temporal sequence of outputs from a single output has broad relevance, including in neuroscience and machine learning. Inspired by ideas in non-equilibrium physics and modern associative memory models, we demonstrate new representations of sequence recall. Our findings provide potential strategies to improve the learning of temporal data in state-of-the-art neural networks.

Cite

Text

Du et al. "Sequential Pattern Retrieval: New Representations Inspired by Non-Equilibrium Physics and Associative Memory Models." ICLR 2025 Workshops: NFAM, 2025.

Markdown

[Du et al. "Sequential Pattern Retrieval: New Representations Inspired by Non-Equilibrium Physics and Associative Memory Models." ICLR 2025 Workshops: NFAM, 2025.](https://mlanthology.org/iclrw/2025/du2025iclrw-sequential/)

BibTeX

@inproceedings{du2025iclrw-sequential,
  title     = {{Sequential Pattern Retrieval: New Representations Inspired by Non-Equilibrium Physics and Associative Memory Models}},
  author    = {Du, Matthew and Behera, Agnish Kumar and Rao, Madan and Vaikuntanathan, Suriyanarayanan},
  booktitle = {ICLR 2025 Workshops: NFAM},
  year      = {2025},
  url       = {https://mlanthology.org/iclrw/2025/du2025iclrw-sequential/}
}