Learning Shape Descriptions
Abstract
We report on initial experiments with an implemented learning system whose inputs are images of two-dimensional shapes. The system first builds semantic network shape descriptions based on Brady's smoothed local symmetry representation. It learns shape models from them using a modified version of Winston's ANALOGY program. The learning program uses only positive examples, and is capable of learning disjunctive concepts. We discuss the lcarnability of shape descriptions.
Cite
Text
Connell and Brady. "Learning Shape Descriptions." International Joint Conference on Artificial Intelligence, 1985.Markdown
[Connell and Brady. "Learning Shape Descriptions." International Joint Conference on Artificial Intelligence, 1985.](https://mlanthology.org/ijcai/1985/connell1985ijcai-learning/)BibTeX
@inproceedings{connell1985ijcai-learning,
title = {{Learning Shape Descriptions}},
author = {Connell, Jonathan and Brady, Michael},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1985},
pages = {922-925},
url = {https://mlanthology.org/ijcai/1985/connell1985ijcai-learning/}
}