High Order Neural Networks for Efficient Associative Memory Design

Abstract

We propose learning rules for recurrent neural networks with high-order interactions between some or all neurons. The designed networks exhibit the desired associative memory function: perfect storage and retrieval of pieces of information and/or sequences of information of any complexity.

Cite

Text

Dreyfus et al. "High Order Neural Networks for Efficient Associative Memory Design." Neural Information Processing Systems, 1987.

Markdown

[Dreyfus et al. "High Order Neural Networks for Efficient Associative Memory Design." Neural Information Processing Systems, 1987.](https://mlanthology.org/neurips/1987/dreyfus1987neurips-high/)

BibTeX

@inproceedings{dreyfus1987neurips-high,
  title     = {{High Order Neural Networks for Efficient Associative Memory Design}},
  author    = {Dreyfus, Gérard and Guyon, Isabelle and Nadal, Jean-Pierre and Personnaz, Léon},
  booktitle = {Neural Information Processing Systems},
  year      = {1987},
  pages     = {233-241},
  url       = {https://mlanthology.org/neurips/1987/dreyfus1987neurips-high/}
}