logoalt Hacker News

charcircuityesterday at 10:35 AM1 replyview on HN

The model can converge towards such a state even if randomly initialized.


Replies

hodgehog11yesterday at 12:16 PM

Both you and the comment above are correct; initializing with iid elements ensures that correlations are not disastrous for training, but strong correlations are baked into the weights during training, so pretty much anything could potentially happen.