Update from Nil on the "proto-AGI" project -- which is basically oriented toward making the simplest possible purely experiential embodied learning work using OpenCog ... and then after that building up via adding more and more of the fancy AI we have in OpenCog into this context...
https://github.com/singnet/rocca/blob/master/doc/proto-agi-early-progress-report-and-planning.md Basically, he and Kasim and Eman have now gotten some extremely simplistic learning (chasing a food pellet) in an extremely simplistic 2D environment to work using Atomspace-y knowledge representation and pattern mining. Next steps are to port from the simplistic environment to Minecraft and to gradually introduce more AI (PLN and not just pattern mining, more flexible sorts of predictive implications, etc.). -- Ben Goertzel, PhD http://goertzel.org “Words exist because of meaning; once you've got the meaning you can forget the words. How can we build an AGI who will forget words so I can have a word with him?” -- Zhuangzhi++ -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/opencog/CACYTDBer8m4NJGV38NwwXOoUtMWs62Gxcs5TMRQROcDiNt3whw%40mail.gmail.com.
