Completed
Get painters to the training data on each worker
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Practical Privacy-Preserving Machine Learning in Python
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Introducing myself
- 3 Why privacy?
- 4 Machine learning is hungry for data
- 5 What data should we worry about?
- 6 The simplest way to keep data private
- 7 Wash away your personal data
- 8 But without collecting the data
- 9 Differential privacy
- 10 TensorFlow Privacy
- 11 The epsilon concept
- 12 Encrypt a trained model
- 13 When to use encrypted ML
- 14 Create virtual workers
- 15 Get painters to the training data on each worker
- 16 Send the model weights to each worker
- 17 Train the model on each worker
- 18 Send the weights back to the model owner
- 19 Send the loss back to the model owner
- 20 What's missing?
- 21 When to use federated learning
- 22 Caveats
