State-of-the-art convolutional networks easily memorize random labels and unstructured noise images, indicating that generalization in deep learning cannot be explained by traditional capacity or regularization arguments.
The CIFAR10 dataset contains 50,000 training and 10,000 validation images, split into 10 classes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2016 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Understanding deep learning requires rethinking generalization
State-of-the-art convolutional networks easily memorize random labels and unstructured noise images, indicating that generalization in deep learning cannot be explained by traditional capacity or regularization arguments.