AI for High-Stakes Decision Making with Hima Lakkaraju - #387
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
Navigating Fairness in Machine Learning
This chapter traces the speaker's journey from foundational studies in India to specializing in fair and interpretable machine learning. It examines the challenges of ensuring interpretability and fairness in complex algorithms used in high-stakes decision-making areas like criminal justice and healthcare. Through discussions on bias, trust, and the implications of misleading explanations, the chapter highlights the critical need for transparency in AI systems.
Transcript
Play full episode
