Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations.
Alexander BinderLeander WeberSebastian LapuschkinGrégoire MontavonKlaus-Robert MüllerWojciech SamekPublished in: CoRR (2022)
Keyphrases
- neural network
- artificial neural networks
- bp neural network
- neural network is trained
- neural network model
- privacy preserving
- back propagation
- back propagation neural network
- feed forward
- image reconstruction from projections
- network architecture
- genetic algorithm
- neural nets
- deep learning
- backpropagation neural network
- databases
- radial basis function
- information systems
- training set
- pattern recognition
- self organizing maps
- causal models
- hybrid neural network
- database
- feature selection
- decision trees
- high level
- feedforward neural networks
- feed forward neural networks
- network model
- multi layer
- knn
- fuzzy logic
- fault diagnosis