@Richard and @Matt, i was getting the feeling this may be the case. Sadly i don't think i can offer any valuable input until i am in a place where i am familiar with the code and it's inner workings.
How many months/years would you estimate this domain being in a more suitable place for vision work? This is a digression, apologies. Could you perhaps do a tutorial exploring it's strength and weaknesses compared to 'conventional' machine learning approaches? On Wed, Sep 24, 2014 at 5:31 AM, Matthew Taylor <[email protected]> wrote: > I don't think NuPIC is ready for serious vision work yet. A stable way > to create hierarchies is necessary for anything significant. > --------- > Matt Taylor > OS Community Flag-Bearer > Numenta > > > On Tue, Sep 23, 2014 at 10:25 AM, Richard Crowder <[email protected]> > wrote: > > @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 > >>> > >> > > > >
