Permuted MNIST
Introduced by Goodfellow et al. in An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
Permuted MNIST is an MNIST variant that consists of 70,000 images of handwritten digits from 0 to 9, where 60,000 images are used for training, and 10,000 images for test. The difference of this dataset from the original MNIST is that each of the ten tasks is the multi-class classification of a different random permutation of the input pixels.
Source: Lifelong Learning with Dynamically Expandable NetworksBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Permuted MNIST
|
RMN
|
|||
|
Permuted MNIST
|
HVCL
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
