Optimizing for Interpretability in Deep Neural Networks with Tree Regularization.
Mike WuSonali ParbhooMichael C. HughesVolker RothFinale Doshi-VelezPublished in: CoRR (2019)
Keyphrases
- neural network
- tree structure
- fuzzy decision trees
- regularization methods
- pattern recognition
- multi layer
- fuzzy logic
- genetic algorithm
- tree models
- index structure
- expert systems
- self organizing maps
- prior information
- b tree
- artificial neural networks
- fuzzy systems
- training process
- objective function
- support vector
- tree construction
- multi layer perceptron
- spanning tree
- network architecture
- feed forward
- nearest neighbor
- back propagation