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">></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.1991.139782Markdown
[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.1991.139782BibTeX
@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/}
}