When an Atom is used by a cognitive process its STI gets boosted
("stimulated"), along with (to a much lesser degree) its LTI value
The ECAN module has an importance-spreading agent that spreads STI and
LTI values around along the links in the Atomspace
That's what's happening now; fancier
Hi,
Thank you for the example.
Perhaps i can ask a follow up question:
How are the STI values set (how do we know what is relevant for now), at
what time and which processes in open cog are responsible for them. I
assume that STI values are set for whole groups of atoms.
When and for what
Hi,
InheritenceLink Nageen human
strength - represents True/false
Confidence - expresses degree of strength, expresses how certain/
uncertain the strength is.
InheritenceLink Nageen human <.9, .9>
InheritenceLink Nageen monster <.9, .1>
this indicates that there
This is straightforward: Strength is a measure of likelihood — it can be
thought of as a probability, while confidence is a measure of how confident one
is in the strength value. Confidence is related to the value of count. The more
pieces of evidence upon which the strength is determined, the
When you use MOSES for supervised classification, it's doing something
similar to a supervised learning algorithm... the advantage of MOSES
in that case is mostly that it tends to come up with classification
rules that are both accurate and concise (if the parameters are tuned
well), whereas e.g.
Another question is that how atomspace is different from chunking technique?Can
we merge chunking with atoms concept??Is there any representation of featuers
like chunk with dimension/value pairs?
Sent from my Samsung Galaxy smartphone.
Original message From: 'Nil Geisweiller'
Dear all, Can anyone here explain in detail tge concept of truth value-stregnth
-confidence-countWhat is the concept of attention value.Explain with example
please
Sent from my Samsung Galaxy smartphone.
Original message From: 'Nil Geisweiller' via opencog
> Yeah Nil. I think, the output is not in the suitable format to run FC/BC.
> i extracted R2L parses and it is like the following:
((ImplicationLink (stv 1 1)
(PredicateNode "for@bd1dfde9-6b3c-4b90-912e-c0f9815cf2b1" (stv
9,7569708e-13 0,0012484395))
(PredicateNode "for" (stv
Vishnu,
I don't know if the NLP pipeline is mature enough to process that...
After you've parsed the sentence you may check whether it has produced
knowledge that is similar to the criminal example
https://github.com/opencog/atomspace/blob/master/tests/rule-engine/criminal.scm
I don't think