Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science.
Charlotte LohThomas ChristensenRumen DangovskiSamuel KimMarin SoljacicPublished in: CoRR (2021)
Keyphrases
- data sets
- prior knowledge
- learning algorithm
- data points
- small number
- human experts
- data analysis
- background knowledge
- database
- statistical analysis
- bayesian methods
- learning process
- data sources
- online learning
- raw data
- sensor data
- computer systems
- synthetic data
- high dimensional data
- data mining techniques
- image data
- high quality
- learning systems
- high dimensional
- spatial data
- computer science
- noisy data
- data quality
- learning models
- learning community
- hidden variables
- machine learning
- earth science