Explanation, irrelevance and statistical independence

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


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.
Original languageEnglish GB
Title of host publicationProceedings of the ninth National conference on Artificial intelligence-Volume 1
StatePublished - 1991

Cite this