Semantics and explanation: why counterfactual explanations produce adversarial examples in deep neural networks.
Kieran BrowneBen SwiftPublished in: CoRR (2020)
Keyphrases
- neural network
- generating explanations
- pattern recognition
- logical framework
- causal reasoning
- domain theory
- multi agent
- fuzzy logic
- genetic algorithm
- feed forward
- formal semantics
- explanation based learning
- fuzzy systems
- associative memory
- multilayer perceptron
- neural network model
- logic programming
- artificial neural networks
- data mining