Using the Representation in a Neural Network's Hidden Layer for Task-Specific Focus of Attention
Abstract
In many real-world tasks, the ability to focus attention on the important features of the input is crucial for good performance. In this paper a mechanism for achieving task-specific focus of attention is presented. A saliency map, which is based upon a computed expectation of the contents of the inputs at the next time step, indicates which regions of the input retina are important for performing the task. The saliency map can be used to accentuate the features which are important, and de-emphasize those which are not. The performance of this method is demonstrated on a real-world robotics task: autonomous road following. The applicability of this method is also demonstrated in a non-visual domain. Architectural and algorithmic details are provided, as well as empirical results.
Cite
Text
Baluja and Pomerleau. "Using the Representation in a Neural Network's Hidden Layer for Task-Specific Focus of Attention." International Joint Conference on Artificial Intelligence, 1995. doi:10.21236/ada296386Markdown
[Baluja and Pomerleau. "Using the Representation in a Neural Network's Hidden Layer for Task-Specific Focus of Attention." International Joint Conference on Artificial Intelligence, 1995.](https://mlanthology.org/ijcai/1995/baluja1995ijcai-using/) doi:10.21236/ada296386BibTeX
@inproceedings{baluja1995ijcai-using,
title = {{Using the Representation in a Neural Network's Hidden Layer for Task-Specific Focus of Attention}},
author = {Baluja, Shumeet and Pomerleau, Dean},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1995},
pages = {133-141},
doi = {10.21236/ada296386},
url = {https://mlanthology.org/ijcai/1995/baluja1995ijcai-using/}
}