Introduction to Uncertainty Quantification for Deep Learning

preview_player
Показать описание
A quick 20 min introduction to various UQ methods for Deep Learning:-
- Why is UQ required for Deep Learning
- Bayesian NN
- Monte Carlo Dropout
- MCMC
- Variational Inference
- Laplace Approximation
- Deep Ensembles
- Deep Evidence Regression

Please let me know if I have some errors :)

*sources cited at the end of slides
Рекомендации по теме