Grokking: Generalization beyond Overfitting on small algorithmic datasets (Paper Explained)
Published October 7, 2021
Views 85.0K | Likes 2.96K | Comments 243
At a glance
Views
85,038
Likes
2,969
Comments
243
Performance vs. channel
Outlier score
Engagement rate
More features coming
We're working on new analytics and tools. Stay tuned.
About
#grokking #openai #deeplearning Grokking is a phenomenon when a neural network suddenly learns a pattern in the dataset and jumps from random chance generalization to perfect generalization very suddenly. This paper demonstrates grokking on small algorithmic datasets where a network has to fill in binary tables. Inter…
- Published
- October 7, 2021
- Made for kids
- No
More features coming
We're working on new analytics and tools. Stay tuned.