Improving performance of deep learning models with axiomatic attribution priors and expected gradients.
Gabriel G. ErionJoseph D. JanizekPascal SturmfelsScott M. LundbergSu-In LeePublished in: Nat. Mach. Intell. (2021)
Keyphrases
- learning models
- machine learning
- learning algorithm
- loss function
- semi supervised learning
- learning paradigms
- machine learning algorithms
- conditional random fields
- learning tasks
- classification models
- learning problems
- prior knowledge
- information extraction
- pairwise
- feature extraction
- decision trees
- machine learning models