Dual Networks and Their Pattern Classification Properties

Abstract

An artificial neural network (ANN) architecture termed a dual network is proposed for pattern classification problems. Dual network is a network of densely connected simple processing elements and it presents a structured way to implement polynomial classifiers. A supervised learning algorithm is developed for the dual networks, and their ability to solve complex pattern classification problems is verified through experimental studies.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Cite

Text

Patrikar. "Dual Networks and Their Pattern Classification Properties." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139782

Markdown

[Patrikar. "Dual Networks and Their Pattern Classification Properties." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/patrikar1991cvpr-dual/) doi:10.1109/CVPR.1991.139782

BibTeX

@inproceedings{patrikar1991cvpr-dual,
  title     = {{Dual Networks and Their Pattern Classification Properties}},
  author    = {Patrikar, Ajay},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {686-687},
  doi       = {10.1109/CVPR.1991.139782},
  url       = {https://mlanthology.org/cvpr/1991/patrikar1991cvpr-dual/}
}