--- On Sun, 9/21/08, Ben Goertzel <[EMAIL PROTECTED]> wrote: >On Sun, Sep 21, 2008 at 8:08 PM, Matt Mahoney <[EMAIL PROTECTED]> wrote:
>>--- On Sun, 9/21/08, Ben Goertzel <[EMAIL PROTECTED]> wrote: >>>Text compression is IMHO a terrible way of measuring incremental progress >>>toward AGI. Of course it may be very valuable for other purposes... >>It is a way to measure progress in language modeling, which is an important >>component of AGI That is true, but I think that measuring progress in AGI **components** is a very poor approach to measuring progress toward AGI.... >Focusing on testing individual system components tends to lead AI developers >down a path of refining system components for optimum functionality on >isolated, easily-defined test problems that may not have much to do with >general intelligence. A language model by itself can pass the Turing test because it knows P(A|Q) for any question Q and answer A. However, to model a single person the training text should be a transcript of all that person's communication since birth. We don't have that kind of training data, and the result would not be very useful anyway. I would rather use a system trained on Wikipedia, and it doesn't affect the learning algorithms. One can argue that a system isn't AGI if it can't see, walk, experience human emotions, etc. There isn't a compression test for these other aspects of intelligence, but so what? -- Matt Mahoney, [EMAIL PROTECTED] ------------------------------------------- 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=114414975-3c8e69 Powered by Listbox: http://www.listbox.com
