On Wednesday 30 Jul 2003 10:27, Rudi Cilibrasi wrote: > I think it's clear that there will > be some sort of "self-organizing complexity" as Wolfram would phrase it, > but am still trying to decide how we might characterize and measure > different large-scale network behaviors when under the control of different > routing schemes.
Seen as the temptation of using "AI for everything" is becoming too great in this, I'm trying to figure out if self organizing NNs could be used for this in a useful manner. I cannot think of any reason why this might be any better than a good hashing/specialisation function, but it's an idea anyway... Let it never be said that thinking is not dangerous. ;-) Gordan _______________________________________________ devl mailing list [EMAIL PROTECTED] http://hawk.freenetproject.org:8080/cgi-bin/mailman/listinfo/devl
