Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

2 pointsby stygiansonicalmost 3 years ago

1 comment

stygiansonicalmost 3 years ago

Related Twitter thread: <a href="https://twitter.com/awnihannun/status/1542967463100305408" rel="nofollow">https://twitter.com/awnihannun/status/1542967463100305408</a>