> > You have interpreted my below post in an overly defensive manner. > > >
Sorry ... I'm dealing with some other frustrating things this morning so maybe the frustratedness unintentionally rubbed off on this email exchange ... > > > > (Are you saying Novamente is not scaleable to human level without MOSES?) > > > No ... I'm saying OCP is not scalable to human level without **some** highly specialized set of heuristics for procedure learning MOSES is one set of such heuristics, working on Combo trees... If you removed MOSES from OCP, you'd need to replace it with something else, or the system would not be scalable to human-level AI This "something else" could take a lot of forms -- for instance it could be a specialized control scheme for PLN (working directly on the AtomTable), guiding PLN to do inference about procedure learning appropriately ... or there are lots of other possibilities... > > By the way, you didn't answer my question about how it is that you think > the human brain represents declarative and procedural knowledge > differently. I would be interested to know what differences you are > referring to. > I'll respond to that another day -- it's a busy day and that would require me to refresh my memory on various details. On AI I can respond off the top of my head, but not on neuroscience ;-) ben ------------------------------------------- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
