High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach.
Tim PearceAlexandra BrintrupMohamed ZakiAndy NeelyPublished in: ICML (2018)
Keyphrases
- deep learning
- distribution free
- high quality
- prediction intervals
- regression model
- confidence level
- normal distribution
- large deviations
- unsupervised learning
- travel time
- machine learning
- mental models
- vc dimension
- weakly supervised
- standard deviation
- image quality
- probability distribution
- model selection
- multi class
- image sequences