Evaluating Alternative Instance Representations

Saxena, Sharad

doi:10.1016/B978-1-55860-036-2.50118-1

Evaluating Alternative Instance Representations

Sharad Saxena

ICML 1989 pp. 465-468

doi:10.1016/B978-1-55860-036-2.50118-1 /icml/1989/saxena1989icml-evaluating/

Abstract

This paper addresses the problem of evaluating which, among a given set of alternative representations of a problem, is best suited for learning from examples. It is argued that the representation that leads to a simpler function of the input features is best suited for learning. An algorithm for estimating the complexity of the function from a set of examples is proposed. The algorithm was able to correctly identify the better of the two given representations for the two-or-more-clumps problem.

ICML Semantic Scholar

Cite

Text

Saxena. "Evaluating Alternative Instance Representations." International Conference on Machine Learning, 1989. doi:10.1016/B978-1-55860-036-2.50118-1

Markdown

[Saxena. "Evaluating Alternative Instance Representations." International Conference on Machine Learning, 1989.](https://mlanthology.org/icml/1989/saxena1989icml-evaluating/) doi:10.1016/B978-1-55860-036-2.50118-1

BibTeX

@inproceedings{saxena1989icml-evaluating,
  title     = {{Evaluating Alternative Instance Representations}},
  author    = {Saxena, Sharad},
  booktitle = {International Conference on Machine Learning},
  year      = {1989},
  pages     = {465-468},
  doi       = {10.1016/B978-1-55860-036-2.50118-1},
  url       = {https://mlanthology.org/icml/1989/saxena1989icml-evaluating/}
}