Re:Any Deep ReLU Network Is Shallow
by foota on Saturday June 24, 2023 @12:01AM
(#36455419)
Another maybe silly thought, but if any relu network could be written in three layers, does this allow for a hyper efficient ReLu only hardware for ml where the pipeline is fixed?
[ Parent
| on HN ]
See these comments on the same post if not already.
https://news.ycombinator.com/item?id=36453136
Short answer to your question: Not true in general.