Analog Neural Networks as Decoders

Abstract

Analog neural networks with feedback can be used to implement l((cid:173) Winner-Take-All (KWTA) networks. In turn, KWTA networks can be used as decoders of a class of nonlinear error-correcting codes. By in(cid:173) terconnecting such KWTA networks, we can construct decoders capable of decoding more powerful codes. We consider several families of inter(cid:173) connected KWTA networks, analyze their performance in terms of coding theory metrics, and consider the feasibility of embedding such networks in VLSI technologies.

Cite

Text

Erlanson and Abu-Mostafa. "Analog Neural Networks as Decoders." Neural Information Processing Systems, 1990.

Markdown

[Erlanson and Abu-Mostafa. "Analog Neural Networks as Decoders." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/erlanson1990neurips-analog/)

BibTeX

@inproceedings{erlanson1990neurips-analog,
  title     = {{Analog Neural Networks as Decoders}},
  author    = {Erlanson, Ruth and Abu-Mostafa, Yaser},
  booktitle = {Neural Information Processing Systems},
  year      = {1990},
  pages     = {585-588},
  url       = {https://mlanthology.org/neurips/1990/erlanson1990neurips-analog/}
}