On Tue, Apr 2, 2013 at 7:57 PM, Peter Voss <[email protected]> wrote:

>> I can test whether you understand a sequence of symbols by how well you can
>> predict the next one.

> Hardly.  I know the next words in many foreign songs without a clue as to
> what they mean.

Good point. But if you understood the words, you could predict some of
them the first time you heard the song.

But I guess we're just arguing about definitions. Or more precisely,
how to apply an existing definition of a human characteristic to
machines.


--
-- Matt Mahoney, [email protected]


-------------------------------------------
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

Reply via email to