Mitigating belief projection in explainable artificial intelligence via Bayesian teaching

State-of-the-art deep-learning systems use decision rules that are challenging for humans to model. Explainable AI (XAI) attempts to improve human understanding but rarely accounts for how people typically reason about unfamiliar agents. We propose explicitly modelling the human explainee via Bayesi...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Scott Cheng-Hsin, Vong, Wai Keen, Sojitra, Ravi B., Folke, Tomas, Shafto, Patrick
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8110978/
https://www.ncbi.nlm.nih.gov/pubmed/33972625
http://dx.doi.org/10.1038/s41598-021-89267-4

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8110978/
https://www.ncbi.nlm.nih.gov/pubmed/33972625
http://dx.doi.org/10.1038/s41598-021-89267-4

Ejemplares similares