Removing input features via a generative model to explain their attributions to classifier's decisions.
Chirag AgarwalDan SchonfeldAnh NguyenPublished in: CoRR (2019)
Keyphrases
- input features
- generative model
- machine learning algorithms
- probabilistic model
- class labels
- feature values
- classification algorithm
- feature selection
- support vector machine
- em algorithm
- feature subset
- semi supervised
- topic models
- prior knowledge
- activation function
- selected features
- computer vision
- labeled examples
- supervised learning
- expectation maximization
- feature space
- decision trees