Two Case Studies in Cost-Sensitive Concept Acquisition

Abstract

This paper explores the problem of learning from examples when feature measurement costs are significant. It then extends two effective and familiar learning methods, ID3 and IBL, to address this problem. The extensions, CS-ID3 and CS-IBL, are described in detail and are tested in a natural robot domain and a synthetic domain. Empirical studies support the hypothesis that the extended methods are indeed sensitive to feature costs: they deal effectively with varying cost distributions and with irrelevant features.

Cite

Text

Tan and Schlimmer. "Two Case Studies in Cost-Sensitive Concept Acquisition." AAAI Conference on Artificial Intelligence, 1990.

Markdown

[Tan and Schlimmer. "Two Case Studies in Cost-Sensitive Concept Acquisition." AAAI Conference on Artificial Intelligence, 1990.](https://mlanthology.org/aaai/1990/tan1990aaai-two/)

BibTeX

@inproceedings{tan1990aaai-two,
  title     = {{Two Case Studies in Cost-Sensitive Concept Acquisition}},
  author    = {Tan, Ming and Schlimmer, Jeffrey C.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1990},
  pages     = {854-860},
  url       = {https://mlanthology.org/aaai/1990/tan1990aaai-two/}
}