Following is a non exhaustive list of video lectures on the topic of ethics in AI, bias, fairness, interpretability, and similar topics I enjoyed.
The era of blind faith in big data must end | Cathy O'Neil
Kathryn Hume, Ethical Algorithms: Bias and Explainability in Machine Learning
"Privacy: the Last Stand for Fair Algorithms" by Katharine Jarmul
Katharine Jarmul | Keynote: Ethical Machine Learning: Creating Fair Models in an Unjust World
Open the Black Box: an Introduction to Model Interpretability with LIME and SHAP - Kevin Lemagnen
AI, Show Your Work | Michael Capps | TEDxRaleigh
Machine Learning Interpretability, Patrick Hall - H2O World San Francisco
Interpretable Machine Learning
NYAI #20: Ethical Algorithms | Bias and Explainability in Machine Learning Systems
Chief Scientist Alejandro Saucedo - ML explainability, bias evaluation and reproducibility.
Towards interpretable reliable models - Keynote Katharine Jarmul
Programming Your Way to Explainable AI @ O'Reilly AI NY 2017
Cynthia Rudin - Interpretable ML for Recidivism Prediction - The Frontiers of Machine Learning
Explainability of Deep Learning Systems @ SF BayArea Machine Learning Meetup
Finale Doshi-Velez: "A Roadmap for the Rigorous Science of Interpretability" | Talks at Google
Interpretable Machine Learning: Methods for understanding complex models
Measures and Mismeasures of Algorithmic Fairness - Manojit Nandi
Keynote by Agus Sudjianto, Wells Fargo - Interpretable Machine Learning - H2O World San Francisco
Measures and Mismeasures of Algorithmic Fairness - Manojit Nandi
Building Explainable Machine Learning Systems: The Good, the Bad, and the Ugly
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data Scientist, Aviva
"Why Should I Trust you?" Explaining the Predictions of Any Classifier
The ethical dilemma we face on AI and autonomous tech | Christine Fox | TEDxMidAtlantic
iml: A new Package for Model-Agnostic Interpretable Machine Learning
Interactive and Interpretable Machine Learning Models for Human Machine Collaboration
"Explainable Machine Learning Models for Healthcare AI"
Tutorial: 21 fairness definitions and their politics
What-If Tool Overview - People + AI Research (PAIR)
