Turing Machines and Conenctionist networks

[Alexis Wieland]

Well sure, recurrent networks are unquestionably needed to do 
powerful stuff, you're not going to implement a Turing machine
with feed-forward networks alone.  Recurrence allows memory
as found in a computer.  To really harness that power you want 
to "learn" the recurrent part of the network as well, allowing
the system to decide where and when it needs some memory.  BP 
(as well as ART, vect. quant, Boltzman, etc, etc) are all quite 
interesting and powerful, but if we can't figure out how to 
make a net learn where and when recurrence / memory is needed ...
connectionism will probably die out again fairly soon.

alexis.
(UCLA) alexis at cs.ucla.edu     or     (MITRE Corp.) alexis at yummy.mitre.org
             <don't ask, it's a long commute>