ML Anthology

On the Duality Between Mechanistic Learners and What It Is They Learn

Rusins Freivalds, Carl H. Smith
ALT 1993 pp. 137-149
doi:10.1007/3-540-57370-4_43 /alt/1993/freivalds1993alt-duality/

Abstract

All previous work in inductive inference and theoretical machine learning has taken the perspective of looking for a learning algorithm that successfully learns a collection of functions. In this work, we consider the perspective of starting with a set of functions, and considering the collection of learning algorithms that are successful at learning the given functions. Some strong dualities are revealed.

PDF ALT Semantic Scholar

Cite

Text

Freivalds and Smith. "On the Duality Between Mechanistic Learners and What It Is They Learn." International Conference on Algorithmic Learning Theory, 1993. doi:10.1007/3-540-57370-4_43

Markdown

[Freivalds and Smith. "On the Duality Between Mechanistic Learners and What It Is They Learn." International Conference on Algorithmic Learning Theory, 1993.](https://mlanthology.org/alt/1993/freivalds1993alt-duality/) doi:10.1007/3-540-57370-4_43

BibTeX

@inproceedings{freivalds1993alt-duality,
  title     = {{On the Duality Between Mechanistic Learners and What It Is They Learn}},
  author    = {Freivalds, Rusins and Smith, Carl H.},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {1993},
  pages     = {137-149},
  doi       = {10.1007/3-540-57370-4_43},
  url       = {https://mlanthology.org/alt/1993/freivalds1993alt-duality/}
}