Attentional Neural Network: Feature Selection Using Cognitive Feedback
Abstract
Attentional Neural Network is a new framework that integrates top-down cognitive bias and bottom-up feature extraction in one coherent architecture. The top-down influence is especially effective when dealing with high noise or difficult segmentation problems. Our system is modular and extensible. It is also easy to train and cheap to run, and yet can accommodate complex behaviors. We obtain classification accuracy better than or competitive with state of art results on the MNIST variation dataset, and successfully disentangle overlaid digits with high success rates. We view such a general purpose framework as an essential foundation for a larger system emulating the cognitive abilities of the whole brain.
Cite
Text
Wang et al. "Attentional Neural Network: Feature Selection Using Cognitive Feedback." Neural Information Processing Systems, 2014.Markdown
[Wang et al. "Attentional Neural Network: Feature Selection Using Cognitive Feedback." Neural Information Processing Systems, 2014.](https://mlanthology.org/neurips/2014/wang2014neurips-attentional/)BibTeX
@inproceedings{wang2014neurips-attentional,
title = {{Attentional Neural Network: Feature Selection Using Cognitive Feedback}},
author = {Wang, Qian and Zhang, Jiaxing and Song, Sen and Zhang, Zheng},
booktitle = {Neural Information Processing Systems},
year = {2014},
pages = {2033-2041},
url = {https://mlanthology.org/neurips/2014/wang2014neurips-attentional/}
}