sorry, forgot about the convo! In this sense would you consider modelling as reverse engineering?
seems to me is very diff to you both. That's great though as I also believe sci is not a monolith and shouldn't be.
-
-
for context: my objection is that I think solving the problem with understanding NNs – recallhttps://twitter.com/o_guest/status/785731096080183296 …
-
is not solved by doing more software/hardware reverse/forward engineering but actually doing some science.
-
oh that I'm happy to agree with! As for the dennett thing, not really - just some claim he made about linguistics
-
hahaha linguistics omg what a quagmire of poop
End of conversation
New conversation -
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.