Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise.
Spencer FreiYuan CaoQuanquan GuPublished in: CoRR (2021)
Keyphrases
- label noise
- trained neural networks
- active learning
- neural network
- neural learning
- noise tolerant
- rule extraction
- training data
- artificial neural networks
- noise model
- trained neural network
- data mining
- multiple instance learning
- feature space
- image restoration
- high dimensional
- linguistic rules
- e learning
- machine learning