Evidential Deep Learning and Uncertainty

This lecture examines uncertainty estimation in deep learning, focusing on evidential deep learning for regression and classification. It compares likelihood estimation, Bayesian neural networks, and evidential neural networks, including applications to depth estimation and semantic segmentation.

Syllabus

- Introduction and motivation
- Outline for lecture
- Probabilistic learning
- Discrete vs continuous target learning
- Likelihood vs confidence
- Types of uncertainty
- Aleatoric vs epistemic uncertainty
- Bayesian neural networks
- Beyond sampling for uncertainty
- Evidential deep learning
- Evidential learning for regression and classification
- Evidential model and training
- Applications of evidential learning
- Comparison of uncertainty estimation approaches
- Conclusion