For the record, RNNs are Turing-complete and can implement any function: https://stats.stackexchange.com/questions/220907/meaning-and-proof-of-rnn-can-approximate-any-algorithm …https://twitter.com/fchollet/status/1010278944782708737 …
-
No need for RNNs, a simple one-layer feedforward net is already a universal approximator. That statement is utterly useless, too, because only very simple programs can be *learned* from finite data in practice (every tried training a LSTM to sort arbitrary lists?).
These claims, although technically true, are profoundly misleading. Brainfuck is a better Turing-complete substrate for automatic programming than a Conv-LSTM (note than a vanilla RNN is not Turing-complete, btw).
-
-
(Although, it would be pretty shocking if you could *not* come up with simple NN architectures that were Turing-complete -- Turing completeness is an extremely common property for any non-trivial data processing system.)
-
I think the distinction between recurrent and feedforward is that the former are Turing complete (run arbitrary programs) but not the latter
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.