Скачать или смотреть Explainability and Interpretability in AI

QU Fall school 2021 Speaker Series
In this talk, David will cover the need for an understanding of explainability and interpretability in AI from the perspective of experimental psychology.
In particular, he will discuss a leading theory of how humans interpret quantitative stimuli, including ML model outputs, and the implications of this theory for how to design explainable and interpretable systems.

Reference: National Institute of Standards and Technology (NIST) publication: Psychological Foundations of Explainability and Interpretability in Artificial Intelligence, David Broniatowski
Hosted by Sri Krishnamurthy, CFA, CAP , QuantUniversity
Slides at: https://academy.qusandbox.com/market/...