Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training.
Alfred LaugrosAlice CaplierMatthieu OspiciPublished in: ECCV Workshops (5) (2020)
Keyphrases
- neural network
- training algorithm
- training process
- feed forward neural networks
- back propagation
- multi layer perceptron
- recurrent networks
- feedforward neural networks
- neural network training
- training phase
- network architecture
- multi layer
- training patterns
- active learning
- artificial neural networks
- backpropagation algorithm
- activation function
- feed forward
- error back propagation
- network model
- recurrent neural networks
- neural network model
- test set
- multilayer neural network
- image reconstruction from projections
- image segmentation
- train a neural network
- labeled data for training
- hidden layer
- fuzzy logic
- pattern recognition
- genetic algorithm
- machine learning