Linas,

What you just described makes sense then. Certainly does look like a valid 
rule. I am not in the context of this particular problem and the rule made 
sense just not what I expected.

—Matt

Sent from my iPhone

> On Jan 10, 2020, at 2:37 PM, Linas Vepstas <linasveps...@gmail.com> wrote:
> 
> 
> Hi Matt, Hi Alex:
> 
> First Alex: As Nil already noted, the results you posted look reasonable, 
> except that the truth value was insane, given the code snippets you posted. I 
> see two possibilities:
> -- in addition to running your rule, some other rules are running, and 
> generating a different TV. Maybe some other rules you created and forgot to 
> delete? Maybe some other rules in PLN?
> -- there is a bug in python, causing a bogus TV to be set. Seems unlikely but 
> always possible.
> 
> Matt,
> Why do you say "looks nothing like what the PLN deduction rule should look 
> like"?  The point of the URE & chainers was to allow anyone to create 
> arbitrary rule sets, with whatever formulas they wanted.  Now, indeed, this 
> particular rule might not look like a textbook-PLN rule, but it looks like a 
> perfectly valid user-defined rule to me.  (There is also an unrelated 
> conversation about the efficiency of using URE for crisp-logic, but that is 
> for some other discussion thread.)
> 
> --linas
> 
>> On Fri, Jan 10, 2020 at 3:08 PM Matthew Ikle <matt.i...@gmail.com> wrote:
>> Hmmm. The code snippet I saw looks nothing like what the PLN deduction rule 
>> should look like, but rather a heuristic that binarizes the result perhaps 
>> for efficiency or for some specialized use case. As Linas says, Nil might 
>> know more about why that deduction rule is coded the way it is. The actual 
>> deduction rule would be more complex.
>> 
>> —matt
>> 
>>> On Jan 10, 2020, at 1:55 PM, Linas Vepstas <linasveps...@gmail.com> wrote:
>>> 
>>> 
>>> 
>>> On Fri, Jan 10, 2020 at 2:49 PM Alexander Gabriel <goo...@4d6.de> wrote:
>>>> Hi Linas!
>>>>  
>>>>> This is a relatively minor point, and for a demo, scheme or python 
>>>>> formulas are sufficient, but for anything that you expect to run quickly, 
>>>>> the native formulas would be better.
>>>>  
>>>> Thanks for the tip! :)
>>>> Do you have any idea why the formula/code fails to produce proper 
>>>> inference? That would really help me.
>>> 
>>> I don't know how PLN actually works; Nil would be the expert on that.
>>> 
>>> Strange thing is: gmail said "five new messages", so I assumed you and Nil 
>>> were talking about it. But when I clicked through, there weren't any 
>>> messages, like they just disappeared... !??
>>> 
>>> -- 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 opencog+unsubscr...@googlegroups.com.
>>> To view this discussion on the web visit 
>>> https://groups.google.com/d/msgid/opencog/CAHrUA373zoPYi2A%3DBkXV4cz0BVSgDPPYsc6r14QRz3GtnXPb%2BA%40mail.gmail.com.
>> 
>> -- 
>> 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 opencog+unsubscr...@googlegroups.com.
>> To view this discussion on the web visit 
>> https://groups.google.com/d/msgid/opencog/6893E8F3-46C8-4F3D-8466-359A41D09DBF%40gmail.com.
> 
> 
> -- 
> 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 opencog+unsubscr...@googlegroups.com.
> To view this discussion on the web visit 
> https://groups.google.com/d/msgid/opencog/CAHrUA35vSqT9d3jhGjHajP%2BNBjjS0-Gib2s8NXrQUcL9RhxL5w%40mail.gmail.com.

-- 
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 opencog+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/opencog/1D282880-7A49-46EA-9E29-8B14C4029B9E%40gmail.com.

Reply via email to