Neural Networks - test-drb@ccmp.vtda.org

3 Apr 1998

I am talking about either. In truth, I am interested in AI, whose goal
is to approach the functionings of the brain. So, whatever features
each shares, or differes in is fine. But I suppose that "idealized"
networks are what I mean, that is ones in a purely mathematical space.

For one thing, how are the connections made if not randomly? I
thought it was essentially based on the closest free neuron.

What kind of summation is it if not linear? Do you mean that if the
threshold is 5, 4 is more than to times closer than 2? What does that
mean, if anything?
...
 > a certain predetermined level, the neuron sends a
pulse on the  output,
...
   to trigger
other neurons.
 Could someone please complicate the picture for me? 
Are you asking about wet and squishy neural nets or artificial neural
nets?  There's nothing random about the connections of either in a
*functioning* net, but a learning net can have somewhat random
connections.  The "summation" isn't linear in either type of net, and 
the
...
 trigger can be a frequency threshold as well as an
amplitude threshold.

Of course, real neural nets are *much* more complicated and are  affected
...
 by food, sleep, and neuro-transmitter analogues like
LSD.

-- Doug

______________________________________________________
Get Your Private, Free Email at http://www.hotmail.com