The confidence values are key in the belief revision formulas ... if you have two different estimates of the same probability value from different sources and need to know how to weight them, the confidence values give you good weighting factors...
On Tue, Jan 19, 2021 at 1:28 PM Ivan V. <[email protected]> wrote: > > Thank you for the answer. I assume that distincting between probability and > confidence (taking into account only those two orders of probability) has > some benefits. > > Kind regards, > ivan > > uto, 19. sij 2021. u 20:56 Ben Goertzel <[email protected]> napisao je: >> >> Yeah this was all dealt with quite a lot in the original PLN book from >> 2008 or whatever... PLN confidence values are interpreted in terms of >> imprecise probabilities (cf Peter Walley) and indefinite probabilities >> (our own invention), which are both concise ways of describing second >> order probability distributions >> >> You can have n'th order probabilities too, I even wrote a paper once >> on infinite-order probabilities and their use to model the semantics >> of uncertain self-referential statements ;) >> >> ben >> >> On Tue, Jan 19, 2021 at 10:54 AM Ivan V. <[email protected]> wrote: >> > >> > Just a short question relating to truth values, if anyone is interested in >> > discussion: >> > >> > Formulas in Atomspace have two fuzzy truth values associated: probability >> > and confidence. Now, may confidence be described as probability of >> > probability? If so, why not to call it second order probability? And, if >> > so, may there exist a general higher order probability notion? That would >> > be a truth notion that may recursively apply to [initial formula], to >> > [[initial formula] with associated truth value], and so on, producing a >> > pattern: [...[[[initial formula] with associated truth value] with >> > associated truth value] ...]. >> > >> > Is this making any sense? >> > >> > Recent research documents that dr. Goertzel published around here talk >> > about specific distinctive interpretations of probability and confidence. >> > Those are some nice correspondence fitting ideas, but taking the above >> > under consideration, may there exist some general, recursive >> > interpretation that makes use only of one kind of higher order of >> > probability? >> > >> > Kind regards, and hoping not to disturb too much, >> > ivan >> > >> > -- >> > 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/CAB5%3Dj6XFkCtsBNZ1N3cWDidehFAN390-qfx%2BaY3KGxQmWAcpAQ%40mail.gmail.com. >> >> >> >> -- >> Ben Goertzel, PhD >> http://goertzel.org >> >> “He not busy being born is busy dying" -- Bob Dylan >> >> -- >> 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/CACYTDBc6hAWVkxkQy6vawaWyt6Qf3axwSQhd_oavFC%3DsnYOLsg%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 [email protected]. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/CAB5%3Dj6Vigj-EEK5sNFQPZAUfPDTwwOxYimcPwYYOiHtsgR12HQ%40mail.gmail.com. -- Ben Goertzel, PhD http://goertzel.org “He not busy being born is busy dying" -- Bob Dylan -- 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/CACYTDBdx-coHb1wHy-yq_%3DVmHgnU%3Dfd20u3BaCY%2Bjm%2Bgccy0MA%40mail.gmail.com.
