Introduction to Explainable AI

Dive into the world of Explainable AI in this 46-minute TensorFlow ML Tech Talk. Explore a comprehensive taxonomy of machine learning interpretability methods, gain insights through an in-depth implementation of Integrated Gradients, and discover the importance of selecting attribution baselines. Learn about the fundamental concepts of Explainable AI, its significance in modern machine learning, and get a glimpse into future research directions in this field. Enhance your understanding of interpretable ML techniques and their practical applications, equipping yourself with valuable knowledge to create more transparent and accountable AI systems.

- Intro
- What is Explainable AI?
- Interpretable ML methods
- Deepdive: Integrated Gradients IG
- Picking baselines and future research directions