News for hackers. Stuff that matters.

A comment on Any Deep ReLU Network Is Shallow. Parent comment

Re:Any Deep ReLU Network Is Shallow by uoaei on Saturday June 24, 2023 @05:51AM (#36457193)
I would assume the distinction between trained and untrained networks is a constant factor at best.
[ Parent | on HN ]
Re:Any Deep ReLU Network Is Shallow by a1369209993 on Saturday June 24, 2023 @09:04PM (#36464235)
I meant 'trained' networks in contrast to totally-synthetic intentionally-pathlogical networks like my 2abs-1 example. It could be similar to how (Hindley-Milner) type inference is EXPTIME-complete but works fine for ~all real world programs; that just seems unlikely.
[ Parent | on HN ]