On Sun, Sep 12, 2021 at 8:29 AM Adrian Borucki <[email protected]> wrote: > >> ---- >> As to divine intervention vs. bumbling around: I'm still working on >> unsupervised learning, which I hope will someday be able to learn the >> rules of (common-sense) inference. I think I know how to apply it to >> audio and video data, and am looking for anyone who is willing to get >> neck-deep in both code and theory. In particular, for audio and >> video, I need someone who knows GPU audio/video processing libraries, >> and is willing to learn how to wrap them in Atomese. For starters. > > > I might have some time to help with this - I only did a bit of video / audio > processing for ML but I have > some familiarity of AtomSpace, so that part should be easier. >
Wow! That would be awesome! I thought some more about the initial steps. A large part of this would be setting up video/audio filters to run on GPU's, with the goal of being able to encode the filtering pipeline in Atomese -- so that expressions like "apply this filter then that filer then combine this and that" are stored as expressions in the AtomSpace. The research program would then be to look for structural correlations in the data. Generate some "random" filter sequences (building on previously "known good" filter structures) and see if they have "meaningful" correlations in them. Build up a vocabulary of "known good" filter sequences. One tricky part is finding something simple to start with. I imagined the local webcam feed: it should be able to detect when I'm in front of the keyboard, and when not, and rank that as an "interesting" fact. Possibly also detect day-night cycles. A very fancy thing to do would be to notice that faces have two eyes that occur above a mouth, above a chin, symmetrically arranged. That is, "eyes", "mouth" are two "words" of a grammar, and the grammar is very strict: the only grammatical "sentences" are those where the eyes are equidistantly arranged in proportion to a mouth (an isosceles triangle). A goal would be to learn that grammar. If the word "grammar" is confusing, here, I can explain in greater detail. In short, all patterns have grammars, and pattern recognition is the same thing as grammar recognition. This is a three stage project: building enough of an infrastructure to run experiments, and then, running the experiments to see if they work, and then refining the theory when they don't. All three are different skill sets... that's what makes it a challenge. -- Linas -- 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/CAHrUA360PuHKCFqJuqb_S9sbtaUUe%2BKa-fF1-zLk6G1wqVBrHQ%40mail.gmail.com.
