ML Anthology

Numerical Bifurcation Analysis of an Oscillatory Neural Network with Synchronous/Asynchronous Connections

Yukio Hayashi
NeCo 1994 pp. 658-667
doi:10.1162/NECO.1994.6.4.658 /neco/1994/hayashi1994neco-numerical/

Abstract

One of the advantages of oscillatory neural networks is their dynamic links among related features; the links are based on input-dependent synchronized oscillations. This paper investigates the relations between synchronous/asynchronous oscillations and the connection architectures of an oscillatory neural network with two excitatory-inhibitory pair oscillators. Through numerical analysis, we show synchronous and asynchronous connection types over a wide parameter space for two different inputs and one connection parameter. The results are not only consistent with the classification of synchronous/asynchronous connection types in König's model (1991), but also offer a useful guideline on how to construct a network with local connections for a segmentation task.

NeCo Semantic Scholar

Cite

Text

Hayashi. "Numerical Bifurcation Analysis of an Oscillatory Neural Network with Synchronous/Asynchronous Connections." Neural Computation, 1994. doi:10.1162/NECO.1994.6.4.658

Markdown

[Hayashi. "Numerical Bifurcation Analysis of an Oscillatory Neural Network with Synchronous/Asynchronous Connections." Neural Computation, 1994.](https://mlanthology.org/neco/1994/hayashi1994neco-numerical/) doi:10.1162/NECO.1994.6.4.658

BibTeX

@article{hayashi1994neco-numerical,
  title     = {{Numerical Bifurcation Analysis of an Oscillatory Neural Network with Synchronous/Asynchronous Connections}},
  author    = {Hayashi, Yukio},
  journal   = {Neural Computation},
  year      = {1994},
  pages     = {658-667},
  doi       = {10.1162/NECO.1994.6.4.658},
  volume    = {6},
  url       = {https://mlanthology.org/neco/1994/hayashi1994neco-numerical/}
}