bgoertzel
bgoertzel
Seems like a nice syntactic sugar to me... On Thu, Feb 27, 2020 at 12:08 AM Linas Vepštas wrote: > > This is an enhancement request; not sure if it's...
Thanks a lot for the help w/ Mozi Atomese code optimization, Linas ;) Nil, I agree w/ your sense that using the URE to provide a general, easy-to-use tree-walking functionality...
The probability of P(x) implies Q(y) is a bit weird, but if we look at prob[ P(x) and Q(y) ] / prob[ P(x) ] and consider both probabilities as expectations...
ImplicationScopeLink has truth value semantics based on conditional probability, BindLink does not necessarily do so ... On Wed, Nov 9, 2016 at 12:05 AM, Linas Vepštas [email protected] wrote: > However,...
Sure， using predicate node is ok ... On Saturday, July 19, 2014, Sebastian Ruder [email protected] wrote: > Thanks for your comment, @ruiting https://github.com/ruiting. What you > point out sounds reasonable....
I think this is an important area to deal with, because information coming out of the game world is going to have temporal information attached, so it will be very...
> Hi, > > BTW, with regards to whether post-processing is needed, and whether > > EvaluationLink > PredicateNode "after" > ListLink > have@1111 > go@2222 > > is enough...
So the alternative is EvaluationLink PredicateNode "after" EvaluationLink have@123 she@123 lunch@123 Evaluation go@123 she@123 home@123 This alternative constitutes a link that is guaranteed to always represent **what the sentence said**...
Yes, in general, the system won't need to preserve knowledge regarding what it saw in what sentence... as you say, it's retaining the sentence content that matters However (as you...
On Mon, Aug 18, 2014 at 5:29 AM, William Ma [email protected] wrote: > The main point I don't fully understand is this > > seems different because delicious@1234 could get...