ML Anthology

Variability Bias and Category Learning

Joel D. Martin, Dorrit Billman
ICML 1991 pp. 90-94
doi:10.1016/B978-1-55860-200-7.50022-2 /icml/1991/martin1991icml-variability/

Abstract

Humans learn and use knowledge about variability that biases their later learning of new classes of objects. This ability to bias learning has a strong adaptive value, because it permits more effective induction and inductive reasoning. In this paper, we describe a mechanism for learning and using variability biases that was modeled after human abilities. We then demonstrate the functional advantages that humans may achieve by maintaining such information.

ICML Semantic Scholar

Cite

Text

Martin and Billman. "Variability Bias and Category Learning." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50022-2

Markdown

[Martin and Billman. "Variability Bias and Category Learning." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/martin1991icml-variability/) doi:10.1016/B978-1-55860-200-7.50022-2

BibTeX

@inproceedings{martin1991icml-variability,
  title     = {{Variability Bias and Category Learning}},
  author    = {Martin, Joel D. and Billman, Dorrit},
  booktitle = {International Conference on Machine Learning},
  year      = {1991},
  pages     = {90-94},
  doi       = {10.1016/B978-1-55860-200-7.50022-2},
  url       = {https://mlanthology.org/icml/1991/martin1991icml-variability/}
}