Practical AI Friendly federated learning 🌼
21 snips
Dec 7, 2021 Daniel Beutel, co-founder of ADAP and visiting researcher at the University of Cambridge, delves into federated learning and the Flower framework he co-created. He discusses its user-friendly design, practical implementation challenges, and the importance of data privacy. The conversation also highlights the differences between centralized and federated learning, addressing bias issues, and the exciting future of federated learning applications in medical AI. Beutel’s insights reveal how technology can coexist with ethical considerations in AI development.
AI Snips
Chapters
Transcript
Episode notes
Federated Learning Basics
- Federated learning trains models across multiple datasets without sharing data.
- This allows organizations like hospitals to collaborate while respecting privacy regulations.
Predictive Maintenance Example
- Manufacturing companies using the same machine wanted predictive maintenance.
- However, sharing data revealed production rates, so they used federated learning.
Competitive Collaboration
- Federated learning enables collaboration even among competitors without revealing sensitive data.
- It allows training a shared model backbone while keeping the model's head private.