270 citations · 627 across the 15 of their papers we have counts for
6 papers · 1 filter
TED: Teaching AI to Explain its Decisions
Michael Hind, Dennis Wei, Murray Campbell +5
Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions. However,…
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Rachel K. E. Bellamy, Kuntal Dey, Michael Hind +15
Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and priso…
Trusted Multi-Party Computation and Verifiable Simulations: A Scalable Blockchain Approach
Ravi Kiran Raman, Roman Vaculin, Michael Hind +6
Large-scale computational experiments, often running over weeks and over large datasets, are used extensively in fields such as epidemiology, meteorology, computational biology, an…
FactSheets: Increasing Trust in AI Services through Supplier's Declarations of Conformity
Matthew Arnold, Rachel K. E. Bellamy, Michael Hind +10
Accuracy is an important concern for suppliers of artificial intelligence (AI) services, but considerations beyond accuracy, such as safety (which includes fairness and explainabil…
Collaborative Human-AI (CHAI): Evidence-Based Interpretable Melanoma Classification in Dermoscopic Images
Noel C. F. Codella, Chung-Ching Lin, Allan Halpern +3
Automated dermoscopic image analysis has witnessed rapid growth in diagnostic performance. Yet adoption faces resistance, in part, because no evidence is provided to support decisi…
Teaching Meaningful Explanations
Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy +5
The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to…