Скачать
10. Machine Learning Fairness and Biases
Автор: SprintML-Lab
Загружено: 2024-06-10
Просмотров: 247
Описание: We present examples of how machine learning (ML) systems can behave "unfair", and analyze the sources of their behavior and their biases. Then, we dive into different definitions of fairness, including demographic parity, equal opportunity, equalized odds, etc. Finally, we talk about pre-processing, in-processing, and post-processing mitigations to make ML models more fair. As an outlook, we also analyze trade-offs between fairness and privacy and present current challenges and open problems for fair ML.
Не удается загрузить Youtube-плеер. Проверьте блокировку Youtube в вашей сети.
Повторяем попытку...
Повторяем попытку...
Доступные форматы для скачивания:
Скачать видео
-
Информация по загрузке:
