This course on Responsible AI for Engineers aims to educate learners on the challenges and principles of implementing AI responsibly. The course covers topics such as bias, adversarial attacks, unintended consequences, and societal harms. Students will learn about Google's techniques, research, and design practices in ensuring responsible AI. The teaching method includes case studies, discussions on model understanding, secondary metrics, and engineering objectives. This course is intended for engineers and professionals working with AI who are interested in understanding and implementing responsible AI practices.
Overview
Syllabus
Intro
Rons background
Overview
Imagenet
Google Search
Diabetic Retinopathy
Google Assistant
Google Cloud
Problems with AI
disproportionate performance
Compass
Microsoft Twitter
Filter Bubbles
Amazon Search Algorithm
Principles
Digital Wellbeing
Machine Learning AI
Data Cards
Model Cards
Model Interpretation
Local Interpretation
Shapley Values
Integrated gradients
Gradients
Examples
Visualization Tools
Multiple metrics
Secondary models
Over optimizing
Case study fairness
How does prediction change
How effective is this system
What if we generalize
Collecting more data
Changing the loss function
The net effect
Lessons
AI Guidebook
AI Ethics Guidelines
Taught by
GOTO Conferences
