Even biological systems do not start from a completely blank slate, they have a genetic endowment. I would expect that they would allow for a certain amount of "genetics" in any system and thereafter the system would bootstrap itself. But Confucius agrees with you. "He who says it can be done, and he who says it can't be done are both usually correct." Cheers, ~PM.
From: [email protected] Date: Sat, 5 Jan 2013 01:42:25 +0100 Subject: Re: [agi] FW: AAAI Workshop CFP: Learning Rich Representations from Low-Level Sensors To: [email protected] On Fri, Jan 4, 2013 at 10:25 PM, Piaget Modeler <[email protected]> wrote: http://www.marcpickett.com/RepLearn2013/ Right, they prefer automatically derived rather than hand-crafted "learning". I just want to be on record again saying "it can't be done". Sure, General Intelligence excels at finding structure in unstructured data and enriching "fluid", continuous domains with rather quantized concepts and superstructures. But for probabilistic and other reasons I do not expect a blank slate to develop anthropomorphic concepts, ever. AT AGI | Archives | Modify Your Subscription ------------------------------------------- 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
