The count of a probability is the "number of observations" on which that probability is based
The confidence of a probability is a scaling of the count into the interval [0,1] There are both heuristic and rigorous formulas for deriving the confidence associated with the conclusion of a certain probabilistic inference. Many of the PLN rules now use heuristic formulas. In the case of inference based on natural language statements, this is probably fine as the data is not there to feed more rigorous formulas effectively anyway. In the case of inference based on quantitative observations, the more rigorous formulas (based on second order probabilities etc.) would be of value... On Mon, Jan 23, 2017 at 7:01 AM, 'Nil Geisweiller' via opencog <[email protected]> wrote: > Incomplete wikified version of PLN > > http://wiki.opencog.org/w/PLNBook > > the whole book is available online as well somewhere (can't find it ATM). > > Nil > > > On 01/23/2017 03:59 PM, Nil Geisweiller wrote: >> >> The wiki is not very talkative about this... >> >> Ideally you'd need to read the PLN book. >> >> Said briefly the confidence captures the spread of the second order >> distribution over the true unknown probability. If the confidence is 1 >> the spread is null. If the confidence is 0 the spread is uniform, that >> is we know nothing about the true probability. >> >> The spread of the second order distribution shrinks as more evidence >> accumulates, so it depends on the number of observations. There is a >> function to translate the count N (number of observations) into confidence >> >> c = N / (N + K) >> >> so as you may see as the count increases, so does the confidence. This >> function is rather arbitrary, it could be something else, like say 1 - >> std-dev, or anything that is monotonous and has co-domain [0, 1], but it >> has the advantage of being simple. >> >> Hope it's clearer. >> >> Nil >> >> On 01/23/2017 03:14 PM, Apil Tamang wrote: >>> >>> Hi All, >>> What would be the most intuitive (and generally applicable) way of >>> thinking about 'confidence' in the simple-truth-value system? I know >>> stv consists of a 'strength' and a 'confidence' part. The strength, if I >>> remember correctly is representative of the probability of that >>> statement being true. I'm just not sure how to think about the >>> confidence as a guiding metric ... >>> >>> Thanks... >>> >>> >>> >>> -- >>> 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 post to this group, send email to [email protected] >>> <mailto:[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/a60d3ef2-6fad-4576-bc84-b019f87aab4a%40googlegroups.com >>> >>> >>> <https://groups.google.com/d/msgid/opencog/a60d3ef2-6fad-4576-bc84-b019f87aab4a%40googlegroups.com?utm_medium=email&utm_source=footer>. >>> >>> For more options, visit https://groups.google.com/d/optout. > > > -- > 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/58860CB0.2090703%40gmail.com. > > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD http://goertzel.org “I tell my students, when you go to these meetings, see what direction everyone is headed, so you can go in the opposite direction. Don’t polish the brass on the bandwagon.” – V. S. Ramachandran -- 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/CACYTDBehWxyLwrPXFJGQSgA3G6HbR35oPett21Zw8XdcMQaWOQ%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
