Strategies for Teaching Layered Networks Classification Tasks
Abstract
There is a widespread misconception that the delta-rule is in some sense guaranteed to work on networks without hidden units. As previous authors have mentioned, there is no such guarantee for classification tasks. We will begin by presenting explicit counter(cid:173) examples illustrating two different interesting ways in which the delta rule can fail. We go on to provide conditions which do guarantee that gradient descent will successfully train networks without hidden units to perform two-category classification tasks. We discuss the generalization of our ideas to networks with hidden units and to multi(cid:173) category classification tasks.
Cite
Text
Wittner and Denker. "Strategies for Teaching Layered Networks Classification Tasks." Neural Information Processing Systems, 1987.Markdown
[Wittner and Denker. "Strategies for Teaching Layered Networks Classification Tasks." Neural Information Processing Systems, 1987.](https://mlanthology.org/neurips/1987/wittner1987neurips-strategies/)BibTeX
@inproceedings{wittner1987neurips-strategies,
title = {{Strategies for Teaching Layered Networks Classification Tasks}},
author = {Wittner, Ben S. and Denker, John S.},
booktitle = {Neural Information Processing Systems},
year = {1987},
pages = {850-859},
url = {https://mlanthology.org/neurips/1987/wittner1987neurips-strategies/}
}