Interpretable Machine Learning - Data Brew Season 2 Episode 7

Explore interpretable machine learning in this 37-minute Data Brew episode featuring Ameet Talwalkar. Dive into the concept of model interpretability, its relationship with data privacy and fairness, and cutting-edge research in the field. Learn about scale automation, safe model handling, problem definition, user studies, and practical applications. Discover insights on privacy, fairness, neural networks, and taxonomy in machine learning. Gain valuable advice from Ameet's expertise and experience in interpretable machine learning.

Intro
Meet Amit
Amits background
Scale automation
Working with models safely
Problem definition
User studies
Application
Privacy Fairness
Neural Networks
Taxonomy
Advice