ML Anthology

Global Convergence Rate of Recurrently Connected Neural Networks

Tianping Chen, Wenlian Lu, Shun-ichi Amari
NeCo 2002 pp. 2947-2957
doi:10.1162/089976602760805359 /neco/2002/chen2002neco-global/

Abstract

We discuss recurrently connected neural networks, investigating their global exponential stability (GES). Some sufficient conditions for a class of recurrent neural networks belonging to GES are given. Sharp convergence rate is given too.

NeCo Semantic Scholar

Cite

Text

Chen et al. "Global Convergence Rate of Recurrently Connected Neural Networks." Neural Computation, 2002. doi:10.1162/089976602760805359

Markdown

[Chen et al. "Global Convergence Rate of Recurrently Connected Neural Networks." Neural Computation, 2002.](https://mlanthology.org/neco/2002/chen2002neco-global/) doi:10.1162/089976602760805359

BibTeX

@article{chen2002neco-global,
  title     = {{Global Convergence Rate of Recurrently Connected Neural Networks}},
  author    = {Chen, Tianping and Lu, Wenlian and Amari, Shun-ichi},
  journal   = {Neural Computation},
  year      = {2002},
  pages     = {2947-2957},
  doi       = {10.1162/089976602760805359},
  volume    = {14},
  url       = {https://mlanthology.org/neco/2002/chen2002neco-global/}
}