Yeah, true... On Mon, 21 May 2018, 13:41 Nil Geisweiller, <[email protected]> wrote:
> On 05/21/2018 01:48 PM, Ben Goertzel wrote: > > But Nil -- those record-keeping links can be put in an auxiliary > > Atomspace, not necessarily the same Atomspace where the main thrust of > > reasoning is proceeding... > > Yes, but for rules like incremental direct calculation, and TV revision > in general, it seems traces do need to be taken into account as > reasoning is taking place. That doesn't mean they have to pollute the > main atomspace, but it does show that some form of attention allocation > / meta-learning will be necessary. Well, that is true regardless of that > problem, it just adds more weight to the scale. > > Nil > > > > > On Mon, May 21, 2018 at 8:45 AM, 'Nil Geisweiller' via opencog > > <[email protected]> wrote: > >> On 05/19/2018 09:00 PM, Alexey Potapov wrote: > >>> > >>> Our knowledge is built from data. Deduction systems (probabilistic or > not) > >>> lack this connection, while functional PPLs are well-suited for this. > >> > >> > >> Deduction system can be understood very broadly, and may encompass > >> inferences based on PPL models as well. > >> > >> PLN definitely draws, at least in principle, the relationship between > >> deduction and data. > >> > >> ATM in practice it's a bit lacking though, for instance the link > between the > >> TV > >> > >> Implication <TV> > >> P > >> Q > >> > >> obtained from instances of P and Q is forgotten after the inference. > This > >> should be corrected. Meaning the inference rule > >> > >> D ;; <- instances of P and Q > >> |- > >> Implication <TV> > >> P > >> Q > >> > >> should be more something like > >> > >> LinkBetweenDataAndImplication <TV> > >> D ;; <- instances of P and Q > >> Implication > >> P > >> Q > >> d ;; <- new instance pair of P and Q > >> |- > >> LinkBetweenDataAndImplication <TV_update> > >> Cons > >> d > >> D > >> Implication > >> P > >> Q > >> > >> It would also provide an incremental way to calculate the TV as opposed > to > >> batch processing every time. > >> > >> It's kinda scary, computationally wise, but it seems to do well most > >> inference traces need to be recorded, not just conclusions. Yet another > >> meta-learning black hole... > >> > >> Nil > >> > >> -- > >> 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/a9852fa0-fc0d-bedc-7279-750d13ca8599%40gmail.com > . > >> > >> 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/CACYTDBe2Qg3xnv84oqfar2%2BQJW-%3DU-tH4vrH9f6X75yBXSVgeQ%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
