On Tue, Sep 11, 2012 at 2:24 PM, Ben Goertzel <[email protected]> wrote:
> On Tue, Sep 11, 2012 at 6:06 AM, Mike Tintner <[email protected]> 
> wrote:
>> The work is on *static* images? We live in a moving world.
>
> , your indirect suggestion that his work is generally limited to static 
> images is incorrect...

My two rubles on that is that indeed it is more principled to work
with moving images in a "real" world with shadows, insects on the lens
etc, there is no reason to believe that a self-organizing system would
reach the same solution through a "staged", staggered input (eg. 1.
static images 2. obscured static 3. moving 4. obscured moving 5.
morphed moving objects etc).

Of course it is even more important that the AGI architecture was not
there! But learn we can from robotics results, for the same mysterious
reasons that we can learn languages and all those real world things we
do learn.

AT


-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968
Powered by Listbox: http://www.listbox.com

Reply via email to