Does Interpretability of Neural Networks Imply Adversarial Robustness?
Adam NoackIsaac AhernDejing DouBoyang LiPublished in: CoRR (2019)
Keyphrases
- neural network
- pattern recognition
- artificial neural networks
- fuzzy systems
- back propagation
- fuzzy logic
- training process
- multilayer perceptron
- prediction accuracy
- database
- multi agent
- computational efficiency
- feed forward
- connectionist systems
- search algorithm
- data structure
- nearest neighbor
- training data
- information systems
- neural nets
- genetic algorithm
- data mining