News for hackers. Stuff that matters.
Re:Why deep learning works even though it shouldn’t by tastroder on Wednesday October 21, 2020 @03:44AM (#24845631)
I'm not sure that would be a net benefit over research blogs or something like a technical report directly published by a lab/working group to be quite honest. In a few domains I've recently looked at these notes to the editor / commentary sections seem to only be pseudo-reviewed and I'd say the likelihood of an IEEE rubberstamped one pager on perpetual motion would be non-zero.
Re:Why deep learning works even though it shouldn’t by bArray on Wednesday October 21, 2020 @04:57AM (#24845997)
> I'm not sure that would be a net benefit over research

> blogs or something like a technical report directly

> published by a lab/working group to be quite honest.

I think this is kind of the problem, half of this stuff sits on a webpage somewhere completely unread and not really reference-able.

> I'd say the likelihood of an IEEE rubberstamped one pager

> on perpetual motion would be non-zero.

I would hope that each single page would be reviewed with the same integrity as a six pager. Of course, it's not impossible crap leaks through to any conference/journal.