On 9/22/07, Matt Mahoney <[EMAIL PROTECTED]> wrote: > You understand that I am not proposing to solve AGI by using text compression. > I am proposing to test AI using compression, as opposed to something like the > Turing test. The reason I use compression is that the test is fast, > objective, and repeatable. It is less expensive to maintain a compression > benchmark than a Loebner prize.
demo/discussion: http://www.seamcarving.com/ try it: http://rsizr.com/ What are the implications of this for robot vision and memory? I understand that this is not technically AGI. It seems to me that this is approximating the kind of selective importance that we use to remember details about a scene. This is narrow intelligence for preserving the apparent visual object in a picture, but I imagine there would be an analogous process for preserving other data implied by a scene. ----- 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=8660244&id_secret=48869171-de3d2d
