Categorization Under Complexity: A Unified MDL Account of Human Learning of Regular and Irregular Categories

Abstract

We present an account of human concept learning-that is, learning of categories from examples-based on the principle of minimum descrip(cid:173) tion length (MDL). In support of this theory, we tested a wide range of two-dimensional concept types, including both regular (simple) and highly irregular (complex) structures, and found the MDL theory to give a good account of subjects' performance. This suggests that the intrin(cid:173) sic complexity of a concept (that is, its description -length) systematically influences its leamability.

Cite

Text

Fass and Feldman. "Categorization Under Complexity: A Unified MDL Account of Human Learning of Regular and Irregular Categories." Neural Information Processing Systems, 2002.

Markdown

[Fass and Feldman. "Categorization Under Complexity: A Unified MDL Account of Human Learning of Regular and Irregular Categories." Neural Information Processing Systems, 2002.](https://mlanthology.org/neurips/2002/fass2002neurips-categorization/)

BibTeX

@inproceedings{fass2002neurips-categorization,
  title     = {{Categorization Under Complexity: A Unified MDL Account of Human Learning of Regular and Irregular Categories}},
  author    = {Fass, David and Feldman, Jacob},
  booktitle = {Neural Information Processing Systems},
  year      = {2002},
  pages     = {35-42},
  url       = {https://mlanthology.org/neurips/2002/fass2002neurips-categorization/}
}