2 Apr
1998
2 Apr
'98
8:59 p.m.
On Thu, 2 Apr 1998, Max Eskin wrote:
I know we discussed this earlier, so the replies can
be private, if
you wish, but it seems that some people here are familiar with the
field.
Ah, my favorite Off Topic subject!
My question is this. My understanding of neural
networks is a bunch
of neurons, all more or less randomly connected, with one output
and an arbitrary number of inputs; if the sum of the inputs equals
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