Implicit Bias of Adversarial Training for Deep Neural Networks.
Bochen LvZhanxing ZhuPublished in: ICLR (2022)
Keyphrases
- neural network
- training process
- training algorithm
- feedforward neural networks
- deep architectures
- neural network training
- backpropagation algorithm
- neural network structure
- error back propagation
- recurrent neural networks
- feed forward
- multi layer perceptron
- feed forward neural networks
- fuzzy logic
- recurrent networks
- multi layer
- training phase
- deep learning
- training patterns
- neural nets
- neural network model
- back propagation
- pattern recognition
- genetic algorithm
- data sets
- database
- training examples
- activation function
- supervised learning
- support vector machine
- control system
- active learning
- artificial neural networks
- training set
- expert systems
- deep belief networks