Completed
PAC Bayes aka Generalised Bayes
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Statistical Learning Theory for Modern Machine Learning - John Shawe-Taylor
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Learning is to be able to generalise
- 3 Statistical Learning Theory is about high confidence
- 4 Error distribution picture
- 5 Mathematical formalization
- 6 What to achieve from the sample?
- 7 Risk (aka error) measures
- 8 Before PAC Bayes
- 9 The PAC-Bayes framework
- 10 PAC Bayes aka Generalised Bayes
- 11 PAC Bayes bounds vs. Bayesian learning
- 12 A General PAC Bayesian Theorem
- 13 Proof of the general theorem
- 14 Linear classifiers
- 15 Form of the SVM bound
- 16 Slack variable conversion
- 17 Observations
- 18 Deep Network Training Experiments
- 19 Training and Generalisation Results
- 20 A flexible framework
- 21 Conclusions
