<<Yes. That's why I object to the use of the term algorithm applied to this
sort of
<<"AI".
I agree as they are not really heuristic or rules based in any sense that one
can understand to obtain the output. The strategies to train the NN are rules
based like BP (one of the few early ones I know a bit about) though there are a
myriad of new techniques such as quasi-newton, conjugate gradient etc. I think
the battle is lost as they seem to be referred to as algorithms incessantly. I
think the terminology consistency unit (TCU) has met the same fate of
extinction as the special apostrophe unit (SAU) of the grammar police.
RIP, TCU, Mike
--
_________________________________________________________________
Options: http://lists.thomasclausen.net/mailman/listinfo/olympus
Archives: http://lists.thomasclausen.net/mailman/private/olympus/
Themed Olympus Photo Exhibition: http://www.tope.nl/
|