On Fri, Apr 5, 2013 at 11:36 PM, Ben Goertzel <[email protected]> wrote:
> My plan is to hybridize DeSTIN with OpenCog, in such a way as to allow
> PLN-style probabilistic inference and DeSTIN's hierarchical pattern
> recognition to work together....  I believe this will diminish the
> resource requirements for the DeSTIN side of things, compared to what
> they would be otherwise...
>
> The core idea is given here
>
> http://wp.goertzel.org/?p=404

What do you estimate are the computational costs of human level
vision? How many nodes and links on the sub-symbolic and symbolic
sides? How many operations per second? How much memory? What training
data will you use? How much? How do you plan to collect it?

What do you estimate are the computational costs for simpler problems
like reading text, recognizing faces, driving a car, or flying a
drone? Do you plan any such experiments?

In one paper you mention SIFT briefly (model of a fovea). But in your
more recent papers there is no mention of it, but rather of optimizing
the DeSTIN learning algorithm to eliminate redundant copies of
features that differ only in translation, scale, and rotation. SIFT
would not be compatible with translation invariance, but (IMHO) would
be a better optimization. Has there been any more work on SIFT?

--
-- Matt Mahoney, [email protected]


-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com

Reply via email to