Where Once Were Black Boxes, NIST’s New LANTERN Illuminates
Researchers at the National Institute of Standards and Technology (NIST) have developed a new statistical tool that they have used to predict protein function. Not only could it help with …
CFPB Acts to Protect the Public from Black-Box Credit Models Using Complex Algorithms
Today, the Consumer Financial Protection Bureau (CFPB) confirmed that federal anti-discrimination law requires companies to explain to applicants the specific reasons for denying an application for credit or taking other …
Banking on Data: Ethics of Artificial Intelligence and Machine Learning
Join us for a panel discussion with Patrice Ficklin, Aaron Roth, and Nancy Wallace, moderated by Santa Clara University Director of Internet Ethics Irina Raicu. During this session, we will …
NIST’s Explainable AI Workshop
This workshop explored an understanding of explainable AI, based on a draft NIST whitepaper describing four principles of explainable AI. Discussions addressed the roles of explanations in the AI life cycle, how explainable AI fits into the trustworthy AI ecosystem, and what a risk management strategy looks like for explainable AI.
NIST Asks AI to Explain Itself
It’s a question that many of us encounter in childhood: “Why did you do that?” As artificial intelligence (AI) begins making more consequential decisions that affect our lives, we also want …
Draft White Paper on Combinatorial Methods for Explainability in AI and Machine Learning
A draft white paper is now available for comment, An Application of Combinatorial Methods for Explainability in Artificial Intelligence and Machine Learning. This short paper introduces an approach to producing explanations or …