On Tue, Dec 12, 2017 at 9:21 PM, Piaget Modeler <[email protected]> wrote:
> Are there particular components or combinations of components in the > architecture which > are responsible for providing these individual properties. For example > observation means > taking information from the world and storing it (presumably as Atoms). > The robot has a super-crude vision system. It's nearly blind. It can see faces, locate them in 3D space. It has an Intel realsense thingy that returns human body and hand position data, but its .. crude and inadequate. The realsense is not hooked up to the atomspace at the moment. Perhaps we could steal some code or ideas from CogSketch or QSRlib. (google those) Sound: we have speech-to-text, via google. It sort-of-ish works sort-of if you have a good microphone, and no background noise. Otherwise, its not so good. It cannot tell if you are whispering, shouting, angry, serene. It cannot tell if there is an audience that is clapping, booing. It cannot tell if its in a crowded room or an empty room. Turns out sensory input is a really hard problem. > Coordination means > making inferences (creating new atoms) based on existing or newly stored > observations. > Yeah, got a bunch of these subsystems, all doing different things. > Reaction would be a component that gives a reflex response (high > reliability) to incoming > information. > Yeah, we call that the "chatbot" it doesn't think at all. It just does bogus scripted responses. > Deliberation means a component responsible for generating actions that > pursue goals, > and so forth... > We've got parts scattered about for that, partly assembled and partly disassembled. Its PLN and the rule engine and attention allocation and other bits. --linas > > Kindly advise. > > Michael Miller > > > > On Tuesday, December 12, 2017 at 6:17:51 PM UTC-8, Ben Goertzel wrote: >> >> If you mean, which of these is the OpenCog system *intended* to be >> able to demonstrate, and can theoretically manifest according to the >> design, then -- definitely all of them >> >> If you mean, which of these can some openCog based system now >> runnable demonstrate, it's a much more complicated answer, because a >> lot of these things can now be done but in various limited ways, and I >> don't have time to type all the details right now... >> >> Over the next few months here in HK we are making a renewed push at >> getting OpenCog to usefully control the Sophia robot (we did this sort >> of work a year ago and then paused it to focus on various internal >> improvements) ... once this work is all integrated and effectively >> functional, then we will have a system doing all of these things in a >> limited way in the context of controlling the humanoid robot head/arms >> with speech and vision input and speech and movement output.... Nil >> has finished a working PLN forward/backward chainer and we need to do >> a little more work to connect it properly with OpenPsi, and then to >> get all this working properly with our various visual perception tools >> ... once this is done all the things you ask will finally work in a >> simple way with the robot, and we'll then work on making it more >> complex/subtle/intelligent... >> >> ben >> >> On Wed, Dec 13, 2017 at 10:11 AM, Piaget Modeler >> <[email protected]> wrote: >> > I'm a newbie to Open cog, and I have some questions. >> > >> > Of the following properties, which would you say the Open Cog system >> > exhibits: >> > >> > observation (ability to receive input), >> > coordination (ability to create inferences), >> > reminding (ability to recall observations), >> > reaction (ability to respond to incoming stimuli), >> > deliberation (ability to pursue goals), >> > motivation (ability to formulate goals based on needs), >> > simulation (ability to create forward models), >> > meta-control (ability to dynamically adjust its own processes at >> run-time), >> > regulation (ability to correct or reinforce behaviors), >> > compensation (ability to cancel or neutralize undesired outcomes), >> > experimentation (ability to try new actions to gain knowledge), >> > discovery (ability to formulate and test hypotheses), >> > consolidation (ability to forget or compress information). >> > >> > >> > Kindly advise. >> > >> > Michael Miller (Piaget Modeler) >> > >> > -- >> > 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/54ba5ada-4686-4b70 >> -b4c2-ed4e31f01663%40googlegroups.com. >> > For more options, visit https://groups.google.com/d/optout. >> >> >> >> -- >> Ben Goertzel, PhD >> http://goertzel.org >> >> "I am God! I am nothing, I'm play, I am freedom, I am life. I am the >> boundary, I am the peak." -- Alexander Scriabin >> > -- > 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/6ca63d22-949a-483f-bb3d-f2335284be87%40googlegroups.com > <https://groups.google.com/d/msgid/opencog/6ca63d22-949a-483f-bb3d-f2335284be87%40googlegroups.com?utm_medium=email&utm_source=footer> > . > > For more options, visit https://groups.google.com/d/optout. > -- *"The problem is not that artificial intelligence will get too smart and take over the world," computer scientist Pedro Domingos writes, "the problem is that it's too stupid and already has." * -- 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/CAHrUA34EGJqDnSmjsm8HmSCkFALwdCZWQqbbQTtEHtdW2QVt-g%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
