Disclaimer: I didn't not read this entire conversation. Dennis, please read this wiki page: https://github.com/numenta/nupic/wiki/Vision:-Object-Recognition-Using-NuPIC
Subutai did a good job capturing some information about how vision works with the CLA. Other people mention that NuPIC doesn't do hierarchy. That isn't quite correct. It certainly supports hierarchy but we just don't currently use it and it may not help by itself. Temporal pooling is required to slow time as you move up the hierarchy and I am not sure if it is possible to turn it on currently. Without it you won't get the invariance benefit of the hierarchy. That said, I would really like to see a working vision example get put together, even if we don't have temporal pooling implemented yet. It would be a good carrot to go after. For hierarchy, the OPF has a notion of a "network" of regions. This letters you pass input into the bottom and have it flow through the whole network without having to manually pass it from SP to TP to the next CLA. Just wanted to mention this for anyone putting an example together with hierarchy. On Thu, Nov 14, 2013 at 3:53 PM, Fergal Byrne <[email protected]>wrote: > Hi Dennis, > > My mistake, yes, that's the right course. > > Regards, > > Fergal > > > On Thu, Nov 14, 2013 at 10:57 PM, Dennis Stark <[email protected]> wrote: > >> > The HTM is Jeff's over-arching theory of how the neocortex works. The >> CLA is a very detailed model (suitable for implementation in software right >> now) which describes how Layer 3 of a single region recognises spatial >> patterns and learns sequences of those patterns. The CLA (and NuPIC) >> encompasses three of the six principles of HTM, namely Sparse Distributed >> Representations, Online Learning, and Sequence Memory. Hierarchy, Attention >> and Motor Function are TBD right now! >> > Because of the lack of hierarchy in NuPIC, it cannot compete with other >> "some neuroscience" approaches such as Deep Belief Nets for applications >> such as yours. However, these other approaches lack the temporal sequence >> learning which is one of the core attributes of NuPIC. >> >> Thank you for the explanation! This is exactly why I'm writing a small >> library that enables hierarchy (c++ at the moment for speed). Basically I >> have created some code that is relatively fast and mimics CLA in some >> respect (I don't have dutyCycle watcher for boosting at the moment, and >> it's currently does only spacial pooling). The reason I do this to begin >> with, is for easier translation to GPU, and a little glitch of mine - for >> me it's much easier to write something myself then understand how a huge >> library works. It is only when I fail to achieve the result I turn back to >> the library, but by then I already understand everything. >> >> > For categorisation of static images, I would look at Geoff Hinton's >> work (he has a great, and free, course on Udemy). The system he describes >> looks very much like what you're doing. >> >> I found one on Coursera >> https://class.coursera.org/neuralnets-2012-001/lecture/index Is this the >> one? Looks like it has invaluable information there! >> >> > Time-based learning in NuPIC would involve providing a region with a >> varying input and have it learn the invariance. This would not be done by >> giving it a set of real-world, unrelated images, but perhaps by using 3D >> rendering software to feed it a realistic feed of successive, semantically >> consistent frames, just like what we get when we perceive the world. I >> still think we'll have to wait until we have a hierarchy of CLA's before we >> get general vision happening here. >> >> 3D rendering is a great idea! >> >> >> _______________________________________________ >> nupic mailing list >> [email protected] >> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org >> > > > > -- > > Fergal Byrne, Brenter IT > > <http://www.examsupport.ie>http://inbits.com - Better Living through > Thoughtful Technology > > e:[email protected] t:+353 83 4214179 > Formerly of Adnet [email protected] http://www.adnet.ie > > _______________________________________________ > nupic mailing list > [email protected] > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > >
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
