On Wed, Apr 17, 2019 at 12:16 PM 'Nil Geisweiller' via opencog <
[email protected]> wrote:

> On 4/17/19 7:02 PM, James Bolden wrote:
> >
> > is rule learning accomplished, i.e., what subsystem would have dominion
> > over that process?
>
> If we're talking about logical rules, ultimately I suppose they should
> be reasoned out, at least if we want to guaranty that they are correct.
>

I have vague, general ideas about how they can be learned statistically,
but there are various preliminary steps that need to be accomplished
first.  The meaning of the word "correct" is a very interesting
philosophical question. (viz 10-year-olds reason "correctly", despite not
having a firm foundation in Aristotelian logic. three-fourths-of-a-century
of Piaget has elucidated more; the trick is to convert real-life situations
into observational statistics for unsupervised machine learning.)

--linas

-- 
cassette tapes - analog TV - film cameras - you

-- 
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 post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/opencog.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/opencog/CAHrUA377qmM3cMYiBd4tV93K5PkEWXJYVOBvqWvke7L4tatNwA%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.

Reply via email to