ML Anthology

Learning from a Population of Hypotheses

Michael J. Kearns, H. Sebastian Seung
MLJ 1995 pp. 255-276
doi:10.1007/BF00993412 /mlj/1995/kearns1995mlj-learning/

Abstract

We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approximate an unknown target function arbitrarily well. Our motivation includes the question of how to make optimal use of multiple independent runs of a mediocre learning algorithm, as well as settings in which the many hypotheses are obtained by a distributed population of identical learning agents.

PDF MLJ Semantic Scholar

Cite

Text

Kearns and Seung. "Learning from a Population of Hypotheses." Machine Learning, 1995. doi:10.1007/BF00993412

Markdown

[Kearns and Seung. "Learning from a Population of Hypotheses." Machine Learning, 1995.](https://mlanthology.org/mlj/1995/kearns1995mlj-learning/) doi:10.1007/BF00993412

BibTeX

@article{kearns1995mlj-learning,
  title     = {{Learning from a Population of Hypotheses}},
  author    = {Kearns, Michael J. and Seung, H. Sebastian},
  journal   = {Machine Learning},
  year      = {1995},
  pages     = {255-276},
  doi       = {10.1007/BF00993412},
  volume    = {18},
  url       = {https://mlanthology.org/mlj/1995/kearns1995mlj-learning/}
}