SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training.
Rui XuWenkang QinPeixiang HuangHao WangLin LuoPublished in: CoRR (2023)
Keyphrases
- neural network
- training algorithm
- training process
- feedforward neural networks
- multi layer perceptron
- feed forward neural networks
- neural network training
- training patterns
- cmac neural network
- artificial neural networks
- back propagation
- recurrent networks
- neural network model
- adaptive fuzzy
- pattern recognition
- training phase
- backpropagation algorithm
- neural fuzzy
- supervised learning
- train a neural network
- salient object detection
- stock price prediction
- information content
- self organizing maps
- fault diagnosis
- hidden layer
- adaptive neural
- genetic algorithm
- multi agent
- training set
- multilayer neural network
- neural network structure
- vision system
- online learning
- training samples
- radial basis function
- multilayer perceptron
- neural nets
- multi layer