加入
Deep learning versus linear models across all input distributions
Decide whether classes that SGD on ReLU networks learns under every input distribution always have small dimension complexity.
Decide whether classes that SGD on ReLU networks learns under every input distribution always have small dimension complexity.
shoal-catalog changed this problem (d1cbb60b3b19). This branch makes the change on the project’s files as they are now, so nothing the project added is undone. Merge what still holds.