> > > So far, no one who has taken the time to carefully study the detailed > design has > come forward and told me "I think that ain't gonna work." Varying > levels > of confidence have been expressed; and most of all, the opinion has been > expressed that the design is complicated and even though the whole thing > seems to make a lot of sense, there are a heck of a lot of details to be > resolved. > >
I am quite seriously considering publishing the medium-level design for the Novamente Cognition Engine. If I do this, I'll certainly be curious to see the reaction it gets. Obviously, lots of AI scientists will simply react by classifying it as a bunch of wild speculations propped up by a handful of interesting concrete results about various aspects or components of the system. On the other hand, I would hope that a reasonably large group of readers would come to understand why I'm so enthusiastic about the approach. Probabilistic Logic Networks, the book describing the probabilistic logic framework underlying the Novamente Engine, is going to appear in mid-2008. The natural time to publish the Novamente design would be after that, as the overall NM system relies heavily on PLN. -- Ben ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=64086259-18f2f2
