Completed
BNNS perform worse than MAP models under corruption
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Tackling Covariate Shift with Node-Based Bayesian Neural Networks
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Covariate shift
- 3 Bayesian neural networks (BNNs)
- 4 BNNS perform worse than MAP models under corruption
- 5 Node-based Bayesian neural networks
- 6 Approximating the implicit corruption
- 7 Example of implicit corruptions
- 8 Entropy of latent variables and implicit corruptions
- 9 Is a model robust against its own corruptions?
- 10 How robust is a model against the other model's corruptio
- 11 Training a node-based BNN
- 12 Variational inference
- 13 Variational posterior
- 14 Training objective
- 15 Effects of on corruption robustness
- 16 Robust learning under label noise
- 17 Benchmark comparison
- 18 Conclusion
