>>>>> On Tue, 6 Jul 93 18:55:02 GMT, ip001b at uhura.cc.rochester.edu (Ivan Pulleyn) said:
IP> Nntp-Posting-Host: uhura.cc.rochester.edu
>(well... in recent years) people have realised that there are things neural
>nets can do better than the digital computer, and it's revived NN research.
IP> I am confused by what you are refering to here. What do NN's run on,
IP> besides digital computers? All parallel processing can actually be
IP> implemented on serial machines, so that can't be it.
NNs are SIMULATED on digital computers.
Ideally, NNs should be analog machines (... that takes us quite far
back to the past). Unfortunately, the technology is not yet in place
for that. I am a true believer that it is only a matter of time,
As to the original thread, there were many researchers who continued
to work in the area. The names that come to mind are Kohonen,
Grossberg, Marlsberg; there are more of them. They were not in the
spotlight, though. The research money were going mostly to the
classical AI and only when it became apparent that the promises cannot
be deliver (in spite of many important successes), the scientific
world re-discovered NNs. For the yougner generation of scientists it
is very fortunate: we have an almost virgin area of research with lots
of classical works to compare with.
Andrzej Bieszczad >> WELCOME TO THE MACHINE - Pink Floyd <<
Carleton University, Systems & Comp. Engineering, Ottawa, Canada K1S 5B6
Bell-Northern Research, Ltd., P.O. Box 3511 C, Ottawa, Canada K1Y 4H7
Phone: (CU) (613) 788-2600 ext. 5740 (BNR) (613) 763-2259
Email: andrzej at sce.carleton.caandrzej at BNR.CA