Thanks Linas, that is extremely helpful. Can't wait for 0.03 :-)
On Thursday, September 15, 2016 at 11:44:18 AM UTC+8, linas wrote: > > For your reading pleasure, here is version 0.02 of the document. It > details the language processing pipeline. Please review, as it sets the > stage for the next installment. > > Please keep in mind that this document is describing the current code > base, and will be raising design issues for the near-short-term > design+implementation. As such, it is only philosophical or metaphysical to > the point of how that affects specific design decisions. > > Please keep in mind that the current code base *actually works*, and, on a > good day, can be demoed. > > If there are any questions, or any parts that are unclear, or vague, or > obtuse, or seem to involve stupid design decisions, please raise these as > issues. I'll try to fix them. > > --linas > > On Wed, Sep 14, 2016 at 8:49 PM, Ed Pell <[email protected] <javascript:>> > wrote: > >> Noah, All, evolution gives humans and other living things many pre-canned >> functions like edge detectors in the eye. In vision system some people add >> the early edge detectors and some ask the blank slate to figure everything >> out for itself from scratch. My preference is to give the system as much of >> a leg up as possible. Later when we have functioning system we can explore >> the growth from blank slate question. >> >> Self and not-self is a very early learning. I am that which I can control >> the movement of. The other is the warm, soft, and giving entity (Mom and >> Dad). The other becomes the family. Then strangers are discerned and >> apparently rated as dangerous instinctively, then learned as safe and >> not-safe strangers. >> >> If we want to be experimental psychologists we can force the system to >> learn these early lesson from scratch. If we want a functioning embodied >> conversationalist in a reasonable amount of time then let's give it a head >> start. Both are valid pursuits. We have to pick one to start with. >> >> -- >> 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] <javascript:>. >> To post to this group, send email to [email protected] >> <javascript:>. >> 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/7eacea5d-a872-4941-a4de-ba0af793e96e%40googlegroups.com >> >> <https://groups.google.com/d/msgid/opencog/7eacea5d-a872-4941-a4de-ba0af793e96e%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/fa9822ff-c811-4ccc-8c41-b80a18d90837%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
