On Sun, Apr 7, 2013 at 9:42 PM, Steve Richfield <[email protected]>wrote:
> interest in 4 dimensions Very naughty of you Steve to bring up such a vague topic where you know most of the answers anyway 1) we are all doing 2D computing as 3D chips are still in the making 2) as data scientists we do xD computing where x need not correspond to the 3 or 4 or 50 physical dimensions, if the problem space becomes clearer in 5D we create derivative dimensions from our data, if it behaves just fine with 1 or 2 we compress the extra dimensions 3) no AGI will afford to ignore physical reality, but again it may choose to up- or "downsample" it at will, given that all actuators have their physical importance it would shock nobody if the DoFs became Ds, wether conceptually or actually. 4) ANNs are the only domain where we can legitimately talk of high-D "wiring", but you are no doubt aware that 2D and 3D neural topologies are anything but hopeless, rather Turing equivalent, general purpose computers. Why did you put your fingers in this cookie jar? AT ------------------------------------------- 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
