> > Then, is the output of the decoder component a symbolic description of > the scene (which may be a subset of a semantic net )? > > -- > AN
I suppose so. Also the scene description may be merged into the semantic net. So if the signs / concepts are new, they are constructed for the first time. The semantic net is comprised of these signs / concepts. But if the signs / concepts already exist, they are simply activated. That's how I would do it. ~PM ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
