2013 seems an insanely long time ago ;) ... we started with these ideas https://arxiv.org/abs/1401.3372
https://arxiv.org/abs/1703.04368 but have gone some way since... last summer's partial update was https://www.youtube.com/watch?v=ABvopAfc3jY http://agi-conf.org/2018/wp-content/uploads/2018/08/UnsupervisedLanguageLearningAGI2018.pdf But since last summer we have onboarded a new team that does deep-NN language modeling and we are experimenting with using the output of deep-NN predictive models to guide syntactic parsing and semantic interpretation in OpenCog... -- Ben On Mon, Feb 18, 2019 at 3:51 PM Rob Freeman <[email protected]> wrote: > > On Mon, Feb 18, 2019 at 4:01 PM Ben Goertzel <[email protected]> wrote: >> >> *** >> ... >> And likely the way to do this is to set the network oscillating, and >> vary inhibition to get the resolution of "invariants" you want. >> *** >> >> But we are not doing that. Interesting... > > > Cool. Maybe there could be a match. I want hardware to try this. I've been > playing with the open SpiNNaker interface with the European Human Brain > Project. But it's batch jobs, and lots of fiddling with Python interfaces for > neurosimulators. I'd love to collaborate on it. > > I've always thought the set based representations Open Cog was using could be > fitted to what I was doing. > > But I didn't realize you were doing anything like clustering raw sequence > networks on the fly for language. As I recall when I talked to Ruiting in > 2013 she was using rules?? > > I only started looking in detail at networks after 2013. I was trying to fit > it to Jeff Hawkins' sequence networks. I finally figured out the whole thing, > even the "cross-product" in my original formulation, would reduce to > something as simple as diamond shaped "cliques" in the network. But I didn't > know how to isolate them. Then I came across this paper: > > A Network of Integrate and Fire Neurons for Community Detection in Complex > Networks > Marcos G. Quiles, Liang Zhao, Fabricio A. Breve, Roseli A. F. Romero > http://www.sbmac.org.br/dincon/trabalhos/PDF/invited/69194.pdf > > I immediately googled to see if there was any evidence this mapped to > perception experimentally. And found "binding by synchrony" has been observed > since the '80s, but no-one knew why! > > Nice for me, because I'm working from the other direction. I have the > network, and the network predicts binding by synchrony. > > If you want to compare notes and see if there are any cross insights which > could inform, we can talk over email if you like. > > -Rob > Artificial General Intelligence List / AGI / see discussions + participants + > delivery options Permalink -- Ben Goertzel, PhD http://goertzel.org "The dewdrop world / Is the dewdrop world / And yet, and yet …" -- Kobayashi Issa ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T581199cf280badd7-M64fc653756d1a085a150e612 Delivery options: https://agi.topicbox.com/groups/agi/subscription
