Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore critical lessons in machine learning fairness from Google's products and research in this 36-minute conference talk from Google I/O'19. Gain insights into evaluating and improving models using open-source datasets and tools like TensorFlow Model Analysis. Learn techniques to proactively address fairness in product development, covering topics such as human design, data considerations, measurement strategies, and transparency frameworks. Discover practical applications through case studies and understand the importance of commitment to fairness in ML. Equip yourself with valuable knowledge to enhance your machine learning projects and create more equitable AI solutions.
Syllabus
Introduction
Human Design
Why We Care
Welcome
Data
Measurement
Improvement
Transparency Frameworks
Transparency Framework 1
Real Comments
WhatIf Tool
Fairness Indicators
Case Studies
Commitment
Conclusion
Taught by
TensorFlow