Explanation, Irrelevance, and Statistical Independence

Abstract

We evaluate current explanation schemes. These are either insufficiently general, or suffer from other serious drawbacks. We propose a domain-independent explanation system that is based on ignoring irrelevant variables in a probabilistic setting. We then prove important properties of some specific irrelevance-based schemes and discuss how to implement them.

Cite

Text

Shimony. "Explanation, Irrelevance, and Statistical Independence." AAAI Conference on Artificial Intelligence, 1991.

Markdown

[Shimony. "Explanation, Irrelevance, and Statistical Independence." AAAI Conference on Artificial Intelligence, 1991.](https://mlanthology.org/aaai/1991/shimony1991aaai-explanation/)

BibTeX

@inproceedings{shimony1991aaai-explanation,
  title     = {{Explanation, Irrelevance, and Statistical Independence}},
  author    = {Shimony, Solomon Eyal},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1991},
  pages     = {482-487},
  url       = {https://mlanthology.org/aaai/1991/shimony1991aaai-explanation/}
}