The Data Exchange with Ben Lorica Machine Unlearning: Techniques, Challenges, and Future Directions
May 30, 2024
Ken Liu, a Ph.D. student at Stanford, discusses the concept of machine unlearning in AI models. They explore challenges like removing specific data points effectively, evaluating generative AI models, and linking privacy-preserving ML techniques with unlearning. The conversation delves into the evolution of unlearning techniques, highlighting the need for benchmarks and advanced methods for implementation.
Chapters
Transcript
Episode notes
1 2 3 4 5 6 7
Introduction
00:00 • 2min
Exploring Machine Unlearning in AI Models
01:31 • 19min
Challenges of Evaluation and Application-Oriented Benchmarks in Unlearning Tasks
20:42 • 8min
Exploring the Connection Between Privacy-Preserving ML Techniques and Unlearning
28:31 • 2min
Exploring Machine Learning Techniques for Pre-Training and Fine-Tuning Models
30:43 • 2min
Challenges and Evolution of Unlearning in Machine Learning Models
32:47 • 15min
Exploring the Challenges and Techniques of Unlearning in Machine Learning
47:47 • 2min