How Much Can I Trust You? - Quantifying Uncertainties in Explaining Neural Networks.
Kirill BykovMarina M.-C. HöhneKlaus-Robert MüllerShinichi NakajimaMarius KloftPublished in: CoRR (2020)
Keyphrases
- neural network
- pattern recognition
- neural network model
- trust model
- multi layer
- artificial neural networks
- fuzzy logic
- back propagation
- feed forward
- machine learning
- trust management
- activation function
- associative memory
- self organizing maps
- peer to peer
- social networks
- decision making
- information systems
- network architecture
- artificial intelligence
- genetic algorithm
- trust evaluation
- trust propagation