Responsible AI in Practice with Sarah Bird
EPISODE 322
|
DECEMBER
4,
2019
Watch
Follow
Share
About this Episode
Today we continue our Azure ML at Microsoft Ignite series joined by Sarah Bird, Principal Program Manager at Microsoft.
Sarah, whose work lies primarily in machine learning systems, is now focused on bringing machine learning research into production through Azure ML, including responsible AI. At Ignite, Microsoft released a handful of new tools focused on responsible machine learning, including the Azure Machine Learning 'Machine Learning Interpretability Toolkit'. In our conversation, Sarah walks us through this toolkit, detailing use cases and the experience users can expect when using it. We also discuss the idea of changing "Black-Box" models to "Glass-Box Models", Sarah's recent work in differential privacy, including risks and benefits, and her work in the broader ML community, including being a founding member of the MLSys conference.
About the Guest
Sarah Bird
Microsoft
Resources
- Presentation: Responsible AI: Building trustworthy, secure and transparent machine learning
- Azure Machine Learning 'Machine Learning Interpretability Toolkit'
- ONNX
- Pytorch
- SHAP
- LIME
- Article: Microsoft and Harvard to develop privacy platform.
- TWIML Presents: Differential Privacy
- ICML 2019 Invited Talk: The U.S. Census Bureau Tries to be a Good Data Steward in the 21st Century
- Third Conference on Machine Learning and Systems (MLSys)
- Systems for ML Workshop (NeurIPS 2019)
