A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values.
Mukund SundararajanAnkur TalyPublished in: CoRR (2018)
Keyphrases
- parameter values
- neural network
- preprocessing
- artificial neural networks
- significant improvement
- parameter settings
- optimal parameter values
- three dimensional
- computational cost
- empirical studies
- neural nets
- data sets
- machine learning
- image segmentation
- benchmark datasets
- neural networks and support vector machines