--- Mike Dougherty <[EMAIL PROTECTED]> wrote: > 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.
It says a lot about the human visual perception system. This is an extremely lossy function. Video contains only a few bits per second of useful information. The demo is able to remove a large amount of uncompressed image data without changing the compressed representation in our brains by exploiting only the lowest levels of the visual perception function. -- Matt Mahoney, [EMAIL PROTECTED] ----- 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=49123705-a084fd
