ML Anthology

Realization of the "Weak Rod" by a Double Layer Parallel Network

Takashi Matsumoto, Kenji Kondo
NeCo 1994 pp. 944-956
doi:10.1162/NECO.1994.6.5.944 /neco/1994/matsumoto1994neco-realization/

Abstract

The weak rod can be realized by a very natural double layer network with feedback. While the second layer is linear, the first layer is significantly nonlinear. Elements associated with the first layer are called “synaptic fuses.” An MRF argument is used to eliminate the line variables. The network makes what is cut transparent when a crease or a step edge is present.

NeCo Semantic Scholar

Cite

Text

Matsumoto and Kondo. "Realization of the "Weak Rod" by a Double Layer Parallel Network." Neural Computation, 1994. doi:10.1162/NECO.1994.6.5.944

Markdown

[Matsumoto and Kondo. "Realization of the "Weak Rod" by a Double Layer Parallel Network." Neural Computation, 1994.](https://mlanthology.org/neco/1994/matsumoto1994neco-realization/) doi:10.1162/NECO.1994.6.5.944

BibTeX

@article{matsumoto1994neco-realization,
  title     = {{Realization of the "Weak Rod" by a Double Layer Parallel Network}},
  author    = {Matsumoto, Takashi and Kondo, Kenji},
  journal   = {Neural Computation},
  year      = {1994},
  pages     = {944-956},
  doi       = {10.1162/NECO.1994.6.5.944},
  volume    = {6},
  url       = {https://mlanthology.org/neco/1994/matsumoto1994neco-realization/}
}