> One question is: Is probabilistic logic an appropriate method for the > core of an AGI system, given that this AGI system must proceed largely > on observation-based semantics ... > > I think the answer is YES > > Another question is: Is the current OpenCog infrastructure fully ready > to support scalable probabilistic logic on real-time observation > data... > > I think the answer is NOT QUITE
Similarly, we could ask One question is: Is probabilistic programming an appropriate method for the core of an AGI system, given that this AGI system must proceed largely on observation-based semantics ... I think the answer is YES Another question is: Is any currently available probabilistic programming infrastructure fully ready to support scalable probabilistic programming on real-time observation data... I think the answer is NO... or maybe (??) NOT QUITE ... Regarding the comparison btw probabilistic logic and probabilistic programming, I would note that -- dealing with quantifiers and their binding functions in probabilistic logic is a pain in the ass -- dealing with execution traces in probabilistic programming is a pain in the ass [But ofc, to do probabilistic program learning in any AGI-ish sense, you need to be modeling execution traces and all the variable state changes and interrelationships in there etc. ] So there is copious mess about variables, of different sorts, in both paradigms.. ... Semi-relatedly, it seems to me that if one takes the connector approach to proofs, then the set of connectors comprising a proof can be viewed as a set of dependent types -- and a proof then can be translated to a program via following the prescription embodied in the Agda language, but assuming Agda has at its disposal a library function that carries out unification ... First order unification in Agda seems OK https://github.com/wenkokke/FirstOrderUnificationInAgda higher order also seems to work https://github.com/Saizan/miller but may have bigger scalability issues... So the mapping from connector proofs to procedures becomes pretty concrete in this sense ... The paper I linked in my previous email shows how to (for discrete pdfs over finite domains) map probabilistic logic into simple probabilistic programs.... However it only deals with first-order probability distros.... When we extend these methods to 2nd and 3rd order probability distros, we run into the issue that doing probabilistic program learning via MC sampling or anything similar to that becomes extremely slow.... One then wants to do inference to bypass the need for sampling. But what kind of inference? Perhaps PLN type abductive and inductive inference? In this case one needs the probabilistic logic in order to actually do learning over probabilistic programs without incurring unrealistic overhead... ... Overall, my feeling is that probabilistic programming will be better for procedural knowledge, and probabilistic logic will be better for declarative knowledge. Converting between the two will be valuable also. Exactly where each formulation will be most useful, we will need to determine via experiment... -- Ben -- 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 post to this group, send email to opencog@googlegroups.com. 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/CACYTDBcucLAJ5b4M3QDROE4dC7m2_M0-90RncvgMuyCW5Ajryg%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
