Global importance analysis: An interpretability method to quantify importance of genomic features in deep neural networks.
Peter K. KooAntonio MajdandzicMatthew PloenzkePraveen AnandSteffan B. PaulPublished in: PLoS Comput. Biol. (2021)
Keyphrases
- neural network
- detection method
- feature set
- preprocessing
- classification accuracy
- significant improvement
- genetic algorithm
- classification method
- segmentation method
- pattern recognition
- artificial neural networks
- pairwise
- cost function
- feature space
- feature extraction
- image matching
- feature vectors
- image registration
- data analysis
- feature points
- support vector machine svm
- objective function
- neural nets