ML Anthology

An Information-Theoretic Definition of Similarity

Dekang Lin
ICML 1998 pp. 296-304
/icml/1998/lin1998icml-information/

Abstract

Similarity is an important and widely used con-cept. Previous definitions of similarity are tied to a particular application or a form of knowl-edge representation. We present an information-theoretic definition of similarity that is applica-ble as long as there is a probabilistic model. We demonstrate how our definition can be used to measure the similarity in a number of different domains. 1

Semantic Scholar

Cite

Text

Lin. "An Information-Theoretic Definition of Similarity." International Conference on Machine Learning, 1998.

Markdown

[Lin. "An Information-Theoretic Definition of Similarity." International Conference on Machine Learning, 1998.](https://mlanthology.org/icml/1998/lin1998icml-information/)

BibTeX

@inproceedings{lin1998icml-information,
  title     = {{An Information-Theoretic Definition of Similarity}},
  author    = {Lin, Dekang},
  booktitle = {International Conference on Machine Learning},
  year      = {1998},
  pages     = {296-304},
  url       = {https://mlanthology.org/icml/1998/lin1998icml-information/}
}