On Tue, Dec 3, 2019 at 2:42 PM Matt Mahoney <[email protected]> wrote:

>
>
>
>> We are doing vision (Perception from an AGI Perspective
>> <http://www.cis.temple.edu/~pwang/Publication/perception.pdf>), language
>> (Natural Language Processing by Reasoning and Learning
>> <https://github.com/PhillyAGITeam/Website/blob/master/Papers/PAGI-TR-1.pdf>),
>> knowledge base (ConceptNet and WordNet connections), and robotics. For
>> application, see A
>> <https://cis.temple.edu/tagit/events/papers/Hammer.pdf>reasoning based
>> <https://cis.temple.edu/tagit/events/papers/Hammer.pdf> model for
>> anomaly detection in the Smart City domain
>> <https://cis.temple.edu/tagit/events/papers/Hammer.pdf> and Beyond
>> ML/DL: Learning by Reasoning for Smarter Cities and Safer Schools.
>> <https://www.youtube.com/watch?v=s7EtRJatVmg>
>>
>
> I wasn't able to open the first 3 PDF files but the video was very
> interesting. Especially setting up a billion surveillance cameras to detect
> jaywalking. :-/ What roles do OpenCog and OpenNars play in this vision
> system?
>
> In the current version, OpenNARS does inference on the data preprocessed
using DL tools. The paper explains more.

Regards,

Pei


>> Of course there are still many problems to be resolved, though I don't
>> think low-level cognition is harder than high-level cognition, nor that the
>> latter "never was the real problem".
>>
>> Regards,
>>
>> Pei
>>
>> On Tue, Dec 3, 2019 at 11:17 AM Matt Mahoney <[email protected]>
>> wrote:
>>
>>>
>>>
>>> On Mon, Dec 2, 2019, 1:19 PM Eugene Surowitz via AGI <
>>> [email protected]> wrote:
>>>
>>>> You might take a look at Pei Wang's NARS system;
>>>> an 'Open NARS' system is available.
>>>>
>>>
>>> Pei Wang was on this list when it was first founded but left years ago.
>>> NARS (non axiomatic reasoning system) again has the same hardware
>>> limitations of other probabilistic reasoning systems. It lacks vision,
>>> language, speech, and robotics. It also never had a knowledge base or any
>>> useful applications.
>>>
>>> Again, not trying to be critical because it's a really hard problem.
>>> Modeling high level cognitive processing never was the real problem. It's
>>> the petaflops of low level processing tuned by millions of years of
>>> evolution.
>>>
>>>> *Artificial General Intelligence List <https://agi.topicbox.com/latest>*
> / AGI / see discussions <https://agi.topicbox.com/groups/agi> +
> participants <https://agi.topicbox.com/groups/agi/members> + delivery
> options <https://agi.topicbox.com/groups/agi/subscription> Permalink
> <https://agi.topicbox.com/groups/agi/T7116d9f5c1f0551d-M67cd9056c648c0ce9419037b>
>

------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T7116d9f5c1f0551d-M3b02e966acdab2196fcc78dd
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to