3Blue1Brown Video posted an update
But what is cross-entropy? | Compression is Intelligence Part 2
Why it mattersThe video derives cross-entropy from language trees and optimal codes, then applies cross-entropy to LLM pre-training, distillation, and KL divergence.
Discuss: How does cross-entropy connect optimal compression to LLM pre-training, and where does KL divergence change that picture?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.