A collection of relevant resources discussed in the #ethics-research D4D Slack channel.
Fair prediction with disparate impact: A study of bias in recidivism prediction instruments by Alexandra Chouldechova
"Fairness Through Awareness" by Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, Richard Zemel
Equality of Opportunity in Supervised Learning by Moritz Hardt Eric Price Nathan Srebro
Why Is My Classifier Discriminatory?
ProPublica’s “Machine Bias” story A more technical description of their analysis is available here.
“A Broader View on Bias in Automated Decision-Making: Reflecting on Epistemology and Dynamics”
“Make “Fairness by Design” Part of Machine Learning”
“Local Interpretable Model-Agnostic Explanations”
“Anchors: High-Precision Model-Agnostic Explanations”
Google's developer training program on algorithmic fairness.
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias. The AI Fairness 360 API is available here and the documentation is available here.
The Seductive Diversion of ‘Solving’ Bias in Artificial Intelligence
Supposedly ‘Fair’ Algorithms Can Perpetuate Discrimination
Geoff Hinton Dismissed The Need For Explainable AI: 8 Experts Explain Why He's Wrong
Evolving the IRB: Building Robust Review for Industry Research
Interpretable Machine Learning: A Guide for Making Black Box Models Explainable
Fundamentals of Data Visualization.
The Mythos Of Model Interpretability
Manipulating and Measuring Model Interpretability
“Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems”.
Sanity Checks for Saliency Maps
TIP: Typifying the Interpretability of Procedures
Towards A Rigorous Science of Interpretable Machine Learning
European Union regulations on algorithmic decision-making and a "right to explanation"
Accountability of AI Under the Law: the Role of Explanation
Meaningful information and the right to explanation
Explanation in Artificial Intelligence: Insights from the Social Sciences
We Need Transparency in Algorithms, But Too Much Can Backfire
Stealing Machine Learning Models via Prediction APIs
Accountability of AI Under the Law: The Role of Explanation
AI Can Be Made Legally Accountable for Its Decisions
What worries me about AI by Francois Chollet.
Interaction is the key to machine learning applications by Henry Lieberman
IEEE 2018 workshop on **Machine Learning from User Interaction for Visualization and Analytics.
Artificial Intelligence and Ethics.
Responsible AI Practices by Google AI