Towards neural networks that provably know when they don't know.
Alexander MeinkeMatthias HeinPublished in: CoRR (2019)
Keyphrases
- neural network
- pattern recognition
- fuzzy logic
- recurrent neural networks
- fault diagnosis
- activation function
- artificial neural networks
- worst case
- back propagation
- self organizing maps
- neural nets
- fuzzy systems
- training process
- genetic algorithm
- neural network is trained
- neural learning
- rule extraction
- real world
- hidden layer
- support vector
- feed forward
- data sets
- feature selection
- computational complexity