Am I correct in thinking that symbolic computation has a
distinct frame problem, and connectionist/neural networks
do not? I am basing this on the assumption that things like
recurrent, feed foreward/back neural networks can learn and
adapt much more easily than is the case with symbolic
computation.
Secondly, are we yet again crediting humanity with more
reverence than it deserves. If you very suddenly found
yourself on an unknown alien planet, would you initially be
just as stupid as a neural net, because you and the net
would have no prior experience etc., and you would both be
starting from scratch?
This archive was generated by hypermail 2b30 : Tue Feb 13 2001 - 16:23:51 GMT