Hi Luke,
On 10/6/20 11:10 AM, Luke Peterson wrote:
Sorry if that criticism is a bit wooly, but I feel like some “big
picture” explanation is missing, so I don’t have a framework to hang all
the details on.
The big picture, IMHO, is that OpenCog can learn how to allocate
resources, either by creating Hebbian links via mining (in a general
sense) a record of its own behavior, or creating inference control rules
via mining (in a general sense) a record of its own reasoning. It should
eventually acquire the ability to rewrite its own code, starting with
Atomese, and then the layers under, but we're still far from that.
However we do have proto experiments of creating hebbian links and
control rules.
Whether this can work ultimately depends on the environment. If it's too
chaotic it won't work, if it's partially chaotic with attractors that
OpenCog can figure out, then it likely will work. Biology has been able
to learn to somewhat out-perform physics, chemistry, and humanity has
learned to somewhat outperform biology (we're kinda on the top of the
food chain, these days), so clearly we don't live in a completely
chaotic environment (even though it does seem to get more chaotic by the
days).
Here is my guide, although you and anyone else on the mailing list will
likely find it tedious as it’s pretty elementary stuff explained in far
too many words.
https://luketpeterson.github.io/atomspace-bootstrap-guide/
It's really cool you wrote one. I didn't have time to read it yet
hopefully I will in the not too distant future.
Where would you recommend I look next, to get a handle on the
inferencing systems of OpenCog?
I would say have look at the URE and PLN examples
https://github.com/opencog/ure/tree/master/examples/ure
https://github.com/opencog/pln/tree/master/examples/pln
If you want to know more about proto experiments on learning inference
control rules you may read
https://blog.singularitynet.io/introspective-reasoning-within-the-opencog-framework-1bc7e182827
https://blog.opencog.org/2017/10/14/inference-meta-learning-part-i/
Nil
Anyway, thanks a lot, and thanks for your work on OpenCog to date.
-Luke
--
Patrick: Are they laughing at us?
Sponge Bob: No, Patrick, they are laughing next to us.
--
You received this message because you are subscribed to the Google
Groups "opencog" group.
To unsubscribe from this group and stop receiving emails from it, send
an email to [email protected]
<mailto:[email protected]>.
To view this discussion on the web visit
https://groups.google.com/d/msgid/opencog/707E9A4E-1C3E-47B2-BBC6-C7EB5D7FF9D5%40gmail.com
<https://groups.google.com/d/msgid/opencog/707E9A4E-1C3E-47B2-BBC6-C7EB5D7FF9D5%40gmail.com?utm_medium=email&utm_source=footer>.
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/opencog/5088417f-82f6-8f17-b428-85fbbf89cd5b%40gmail.com.
