ML Anthology

Absence of Cycles in Symmetric Neural Networks

Xin Wang, Arun K. Jagota, Fernanda Botelho, Max H. Garzon
NeCo 1998 pp. 1235-1249
doi:10.1162/089976698300017430 /neco/1998/wang1998neco-absence/

Abstract

For a given recurrent neural network, a discrete-time model may have asymptotic dynamics different from the one of a related continuous-time model. In this article, we consider a discrete-time model that discretizes the continuous-time leaky integrat or model and study its parallel, sequential, block-sequential, and distributed dynamics for symmetric networks. We provide sufficient (and in many cases necessary) conditions for the discretized model to have the same cycle-free dynamics of the corresponding continuous-time model in symmetric networks.

NeCo Semantic Scholar

Cite

Text

Wang et al. "Absence of Cycles in Symmetric Neural Networks." Neural Computation, 1998. doi:10.1162/089976698300017430

Markdown

[Wang et al. "Absence of Cycles in Symmetric Neural Networks." Neural Computation, 1998.](https://mlanthology.org/neco/1998/wang1998neco-absence/) doi:10.1162/089976698300017430

BibTeX

@article{wang1998neco-absence,
  title     = {{Absence of Cycles in Symmetric Neural Networks}},
  author    = {Wang, Xin and Jagota, Arun K. and Botelho, Fernanda and Garzon, Max H.},
  journal   = {Neural Computation},
  year      = {1998},
  pages     = {1235-1249},
  doi       = {10.1162/089976698300017430},
  volume    = {10},
  url       = {https://mlanthology.org/neco/1998/wang1998neco-absence/}
}