I was only interested in the particular [static] point - and its general
applicability to vis.ob. recog. - not trying to make a general point re him.
I started to look at his youtube lecture, and he talks pretty well.
-----Original Message-----
From: Ben Goertzel
Sent: Tuesday, September 11, 2012 1:24 PM
To: AGI
Subject: Re: [agi] Discovering physical dimensions
On Tue, Sep 11, 2012 at 6:06 AM, Mike Tintner <[email protected]>
wrote:
Ben:Those papers are somewhere in here I think
http://web.eecs.umich.edu/~kuipers/research/ssh/bootstrap-learning.html
Fantastic work, really...
Just looking at object recognition paper:
http://web.eecs.umich.edu/~kuipers/papers/Xu-crv-11-pcf.pdf
The work is on *static* images? We live in a moving world.
You have cherry-picked one paper that gave you something obvious to
complain about.
Many of the papers listed on that page are about mobile robot control,
involving processing of sensor streams and associated actions.
I don't think Kuipers has a fleshed-out AGI design/plan, he's more
focused on creating relatively simple systems to prove important
conceptual points about AGI. However, your indirect suggestion that
his work is generally limited to static images is incorrect...
--- Ben G
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/6952829-59a2eca5
Modify Your Subscription:
https://www.listbox.com/member/?&;
Powered by Listbox: http://www.listbox.com
-------------------------------------------
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
