🚀 go-pugleaf

Louis Savain (savainl@earthlink.net) wrote:
: In article <60bg0b$cbp$1@now.cirl.uoregon.edu>,
: deej@now.cirl.uoregon.edu (David Joslin) wrote:

: >[...]
: >And now you are back with *another* AI revolution.  Two AI
: >revolutions in just over two years.  Pretty damned impressive.

:   No need to get excited, David.  We are not scientists, just computer
: technologists with some ideas.  Two years ago we got overly enthused
: by some results we obtained using Boolean networks.  We were wrong.
: But we continued to work on our ideas and this time, we think we got
: some important stuff.  You just be patient, amigo.  And, by the way,
: this is not our revolution.  The temporal neuron revolution is coming
: from neurophysiology and computational neuroscience.  Do a little
: search on the web for these names:  Henry Markram, Terrence Sejnowski,
: Cristof Koch and others.  You AI types should keep up with the
: hard-science advances in neurophysiology.  Those folks are much closer
: to the truth than most of you.  Ciao.

You forgot to mention Sutton and Barto. And I do hope that this is not 
yet-another-recurrent-net spinoff. But here is a question: if it does
causal relations, it won't be able to do logical form, right? I mean,
if you represent solely temporally distinct events, what do you do 
about representing simultaneous properties? (I have the greatest respect
for Koch and Sejnowski, of course, but I won't take their word -- if it
exists -- for it).

	-O