@Daniel Matt and co. can point you to early Numenta vision work. From my experience I ran out of time with V1 pre-processing and SDR encoding with OpenCV. I was looking at saliency, saccading, and attention at the time. Making good progress with the Retina class and initial analysis of parvo and magno paths. But still unsure whether some form of R-CNN might be required to handle HOGs, SIFTs, etc. and creating a Cept like SDR first (via the API?) that then feeds into high HTMs. Plus at the time I wasn't sure what network support was in NuPIC and whether needed for simple inference.
On Tue, Sep 23, 2014 at 1:27 PM, John Blackburn <[email protected]> wrote: > Hi Matthew, > > Rather self serving, but I would love to see a tutorial related to the > "bridge" simulation I've been trying to do or similar. I have not got NuPIC > to work yet despite some effort. Basically the difference with Hotgym is we > have 18 sensors, 10 temperature and 8 tilt (ie strain) and we want to make > predictions on all taking account of cross-correlations. So a tutorial with > multiple correlated time series would be great! > > At NPL we monitored a bridge every 5 minutes for 3 years recording all 18 > sensors so I think this data would be a great showcase for a real-world > NuPIC example. We also perturbed the bridge at known times (cutting > supports, adding weights etc) so we know when the anomalies should appear. > > John. > > On Mon, Sep 22, 2014 at 4:57 PM, Matthew Taylor <[email protected]> wrote: > >> I have more tutorials planned, but I'd like some help deciding which >> to do first. Please answer this 1-question poll: >> >> >> https://docs.google.com/forms/d/1GBYWg_-LIaYmOz9EJ5LbFo6N2ot1xv9AA22gaNdENs0/viewform?usp=send_form >> >> Thanks, >> --------- >> Matt Taylor >> OS Community Flag-Bearer >> Numenta >> >> >
