# Literature Review

## Uncertainity Quantification in Deep Learning

[A review of uncertainty quantification in deep learning: Techniques, applications and challenges](https://arxiv.org/pdf/2107.03342.pdf)
### Key Takeaways
- Five sources of uncertainity:
1. Variability in Real World Situations
2. Error and Noise in Measurement Systems
3. Errors in the Model Structure
4. Errors in the Training Procedure
5. Errors Caused by Unknown Data
- Uncertainity Estimation Methods
- Single deterministic methods
- Bayesian methods
- Ensemble Methods
- Test-time augmentation methods
-