GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularization.
Sungyoon LeeHoki KimJaewook LeePublished in: IEEE Trans. Pattern Anal. Mach. Intell. (2023)
Keyphrases
- neural network
- fuzzy logic
- artificial neural networks
- genetic algorithm
- pattern recognition
- recurrent neural networks
- back propagation
- regularization methods
- fuzzy systems
- neural network model
- computational efficiency
- multi agent
- fault diagnosis
- feed forward
- multilayer perceptron
- regularization framework
- denoising
- activation function
- parameter selection
- regularization method
- image processing