Mike, putting together a demo of a machine learning system recognizing objects from simple line drawings would take me less than one month, using textbook technologies. Not worthwhile. Putting together a simple reinforcement learning system doing the same stuff as NM does in that fetch video would not take much more time than that either.
Judging an early-stage AGI project by its demos is not intelligent. -- Ben g On 6/6/07, Mike Tintner <[EMAIL PROTECTED]> wrote:
Peter Voss: Our goal is to create full AGI... Do you have a "proof-of-concept" to use your term? Hawkins has a simple one for his HTM - he shows his system can recognize objects from simple line drawings. That simple will do to begin with.. Novamente, from what I've seen, doesn't have one - unless you count fetching a ball per the demo.. Do you have one? [Nothing on your site suggests so]. ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?&;
----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=231415&user_secret=e9e40a7e
