Suggested Best Practices for Interpreting Deep Learning Models via Input-Level Importance Scores.
Avanti ShrikumarPublished in: AAAI Spring Symposium: Interpretable AI for Well-being (2019)
Keyphrases
- learning models
- learning algorithm
- learning tasks
- machine learning
- classification models
- semi supervised learning
- machine learning algorithms
- loss function
- conditional random fields
- learning problems
- learning paradigms
- machine learning models
- decision trees
- computer vision
- text categorization
- svm classifier
- supervised learning
- artificial neural networks