Français
3. Main families of explicability methods
3.1 Properties of explicability methods
The methods described for explainability in AI are generally classified a priori according to a few properties that indicate to some extent their use cases. We report on the most common terminology.
SCROLL TO TOP3.1.1 Local methods, global methods
Local methods are concerned with explaining the decision of an intelligent system for an individual case, i.e. for a particular input. We could call them punctual, but they often also concern an entire neighborhood of the...
The Ultimate Scientific and Technical Reference
This article is included in
Software technologies and System architectures
This offer includes:
Knowledge Base
Updated and enriched with articles validated by our scientific committees
Services
A set of exclusive tools to complement the resources
Practical Path
Operational and didactic, to guarantee the acquisition of transversal skills
Doc & Quiz
Interactive articles with quizzes, for constructive reading
Main families of explicability methods
Explanation aids: methods, examples
Bibliography
- (1) - WANG (J.) et al - Learning Credible Models. - In : Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (juill. 2018). arXiv : 1711.03190, p. 2417-2426. doi : 10.1145/3219819. 3220070. URL : http://arxiv.org/...
In the Laws section
Proposal for a REGULATION OF THE EUROPEAN PARLIAMENT AND OF THE COUNCIL ESTABLISHING HARMONIZED RULES FOR ARTIFICIAL INTELLIGENCE (ARTIFICIAL INTELLIGENCE LEGISLATION) AND AMENDING CERTAIN UNION LEGISLATIVE ACTS. Brussels, 21.4.2021.
Websites
Royal Society – Projects
https://royalsociety.org/topics-policy/projects
IBM-Explainable AI
https://www.ibm.com/fr-fr/watson/explainable-ai
Kaggle
The Ultimate Scientific and Technical Reference
