artificial neural nets are just a form of tedious (dataset generation) declarative programming done top down (specify form of program as params to a mathematical formula) that are not interrogable (so also hard to debug) and search better the more money you can throw at them.
-
-
-
No magic to it. Each neural net is a big function. I have on my list an example where I show you can rewrite every RELU net as nested expressions of alternating if-then statements & arithmetic. IOW I get what root tweet is trying to say but it doesn't properly apply quite yet
- 1 more reply
New conversation -
-
-
Silly computers! Good thing my rational engagement with concepts reflects the absolute structure of universal law



-
this, but unironically
End of conversation
New conversation -
-
-
People of the 21st century: "We tried to create minds but they just ended up being tangled messes of inscrutable relationships that don't really add up to anything!" David Hume: "...Yes?"
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
That's what I like about it... It's like teaching an earthworm tricks
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
god can you imagine a bunch of damaged neural nets just wandering around damaging other nearby neural nets lol that would suuuuuuck
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
This Tweet is unavailable.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.