Displaying 13 resources


What-If Tool
A GitHub repository for the What-If Tool.
The What-If Tool (WIT) provides an easy-to-use interface for expanding understanding of a black-box classification or regression ML model.


Fairlearn
Fairlearn is an open-source, community-driven project to help data scientists improve fairness of AI systems.

Don’t ask if AI is good or fair, ask how it shifts power
Opinion piece by Pratyusha Kalluri in Nature

An overview of key trustworthiness attributes and KPIs for trusted ML-based systems engineering
When deployed, machine-learning (ML) adoption depends on its ability to actually deliver the expected service safely, and to meet user expectations in terms of quality and continuity of service.

Cooperating with machines
Since Alan Turing envisioned artificial intelligence, technical progress has often been measured by the ability to defeat humans in zero-sum encounters (e.g., Chess, Poker, or Go).

Should we fear the robot revolution? (The correct answer is yes)
Advances in artificial intelligence and robotics may be leading to a new industrial revolution. This paper presents a model with the minimum necessary features to analyze the implications for inequality and output.