Please Stop Doing "Explainable" ML - Cynthia Rudin
Cynthia Rudin, a Faculty Associate at the Berkman Klein Center, on the important differences between building interpretable machine learning systems and retrospectively explaining the outputs of "black box" systems. Full paper available in Nature: https://www.nature.com/articles/s42256-019-0048-x
Видео Please Stop Doing "Explainable" ML - Cynthia Rudin канала The Berkman Klein Center for Internet & Society
Видео Please Stop Doing "Explainable" ML - Cynthia Rudin канала The Berkman Klein Center for Internet & Society
Показать
Комментарии отсутствуют
Информация о видео
19 августа 2019 г. 18:20:40
00:10:13
Другие видео канала
Interpretability vs. Explainability in Machine LearningInterpreting ML models with explainable AICynthia Rudin - Interpretable ML for Recidivism Prediction - The Frontiers of Machine LearningSelf taught Machine Learning Researcher@Google-Brain, on Interpretability & more | Sara HookerScott Lundberg, Microsoft Research - Explainable Machine Learning with Shapley Values - #H2OWorldInterpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data Scientist, AvivaExplainability, Fairness in AI & Excelling at Research | Dr. Himabindu LakkarajuIntroduction to Explainable AI (ML Tech Talks)Current Approaches in Interpretable Machine Learning with Professor Cynthia RudinThe Science Behind InterpretML: Explainable Boosting MachineExplainable AI Cheat Sheet - Five Key CategoriesMaking AI Human Again: The Importance of Explainable AI (XAI)Colombia Chapter - San Pablo Community NetworkWhat Is Explainable AI? | Explainable vs Interpretable Machine LearningExplainable AI via Computational Argumentation"Why Should I Trust you?" Explaining the Predictions of Any ClassifierWhat is Interpretable Machine Learning - ML Explainability - with Python LIME Shap TutorialInterpretability Beyond Feature AttributionAnca Dragan | Intro to Experiment Design | Good Citizens of Robotics Research